{"generated_at":"2026-10-14T20:07:22+00:00","item":{"added_at":"2026-09-09","analysis_method":"independent_manual_review_2026-10-10","assessment_status":"provisional","auth_posture":"auth_required","category":"Web Connector","confidence":"medium","description":"Creates, runs and troubleshoots QA Wolf end-to-end tests from Claude. Explore an app in a cloud browser, review a test outline and approve implementation. Requires a QA Wolf account, with live links for following progress.","did":"b2a5ffae-648b-407d-a8c4-78ce7a35afee","documentation_url":"https://docs.qawolf.com/qawolf/coding-agents/get-started#create-your-first-flow","editorial_description":{"extended_description":"Tools inspect browser sessions, run or retry flows, diagnose failures and manage issues, tags and environments. The connector can execute snippets, import packages, change environment variables and send test-workflow emails.","schema_version":1,"summary":"Creates, runs and troubleshoots QA Wolf end-to-end tests from Claude.\nExplore an app in a cloud browser, review a test outline and approve implementation.\nRequires a QA Wolf account, with live links for following progress."},"homepage_url":"","icon":"https://qawolf.com/","id":"b2a5ffae-648b-407d-a8c4-78ce7a35afee","installs":0,"last_scanned":"","license":"","long_description":"Tools inspect browser sessions, run or retry flows, diagnose failures and manage issues, tags and environments. The connector can execute snippets, import packages, change environment variables and send test-workflow emails.","manual_assessment":"high","manual_review":{"all_findings":[{"evidence":"These tools execute code/actions in cloud test runners.","reasoning":"They are arbitrary runtime automation.","risk_type":"code_execution","severity":"high","title":"Imports packages, evaluates snippets and performs browser/mobile actions","triggering_tools_or_skills":["runner_importPackage","runner_evaluateSnippet","runner_performAction","runner_runFlow"]},{"evidence":"The tools operate interactive browser/device sessions.","reasoning":"They can act on tested applications.","risk_type":"browser_control","severity":"medium","title":"Controls cloud browser/mobile runners","triggering_tools_or_skills":["runner_launch","runner_performAction","runner_inspectMobile"]},{"evidence":"Email sends externally as the configured test identity.","reasoning":"It is user-representative messaging.","risk_type":"messaging_as_user","severity":"high","title":"Sends email and messages to QA agents","triggering_tools_or_skills":["email_send","agent_send"]},{"evidence":"These tools administer test environments and potentially secrets.","reasoning":"They are privileged configuration actions.","risk_type":"credential_admin","severity":"high","title":"Creates/updates environments and reads/sets variables","triggering_tools_or_skills":["environment_create","environment_getVariable","environment_setVariable","environment_deleteVariable"]},{"evidence":"The tools control cloud test infrastructure.","reasoning":"They launch/stop production QA workloads.","risk_type":"deployment_infrastructure","severity":"high","title":"Creates/runs/stops/terminates test executions","triggering_tools_or_skills":["run_create","runner_launch","runner_stopRun","runner_terminate"]}],"assessment_status":"provisional","auth_and_scopes":"Authentication scopes QA Wolf tests, environments, runners, email and agents.","blocked_missing_evidence":null,"confidence":"medium","displayed_risk":"high","evidence_completeness":"partial","manual_overall_risk":"high","official_sources":[{"accessed_at":"2026-10-10T20:24:37Z","url_or_path":"plutosecurity/plutonium@b749c8dc43536c794409be9805edd48063f045e2:app/data/conn/claudesec/b2a5ffae-648b-407d-a8c4-78ce7a35afee.json","what_it_proves":"Candidate PR #125 record identity (name \"QA Wolf\", publisher, type web_connector) and 49 stored tool names; no tool descriptions stored"},{"accessed_at":"2026-09-22T10:46:07Z","url_or_path":"https://api.anthropic.com/api/directory/servers?verified_tier=anthropic,partner,community (snapshot claude-directory-all-tiers-2026-09-22.json)","what_it_proves":"Official Claude Directory listing https://claude.ai/directory/b2a5ffae-648b-407d-a8c4-78ce7a35afee: complete tool_names inventory (49 tools), remote streamable-http endpoint https://app.qawolf.com/api/mcp, auth_posture auth_required, directory tier community"}],"primary_reason":"QA Wolf executes code/browser actions, sends email and administers test environments.","provisional_risk":null,"publication_recommendation":"accept","requires_runtime_verification":true,"review_key":"claude:b2a5ffae-648b-407d-a8c4-78ce7a35afee","reviewed_at":"2026-10-10","reviewer_notes":"Reviewed all 49 tools.","risk_domains":{"arbitrary_network_access":"false","authz_ambiguity":"unknown","browser_control":"false","credential_or_admin_actions":"true","deletes_data":"true","deployment_or_infrastructure":"true","dynamic_hidden_actions":"true","filesystem_or_repo_access":"true","forwards_data_to_third_party":"true","modifies_data":"true","persistent_credentials":"true","prompt_injection_exposure":"true","provenance_uncertainty":"true","reads_private_data":"true","runs_code_or_queries":"true","sends_messages_as_user":"true","spends_or_moves_money":"false"},"tools_or_skills_reviewed":49,"tools_or_skills_total":49},"name":"QA Wolf","needs_runtime_verification":true,"plutonium_url":"https://plutonium.pluto.security/detail.html?planet=claudesec&did=b2a5ffae-648b-407d-a8c4-78ce7a35afee&utm_source=plutonium_analysis_skill&utm_medium=claude_skill&utm_campaign=connector_risk_assessment","privacy_policy_url":"https://www.qawolf.com/legal/privacy-policy","provisional_risk":null,"publication_recommendation":"accept","publisher":"QA Wolf Inc.","publisher_url":"https://qawolf.com/","remote_url":"https://app.qawolf.com/api/mcp","repository_url":"","risk":"high","risk_severity":"high","security_risks":[{"description":"This connector can execute code, commands, queries, or dynamically selected actions. Review findings: They are arbitrary runtime automation.","evidence":"Imports packages, evaluates snippets and performs browser/mobile actions: These tools execute code/actions in cloud test runners.","manual_risk_type":"code_execution","remediation":{"block_tool_categories":["code_execution"],"steps":["Run only in a sandbox with least-privilege credentials and strict resource limits.","Disable generic execution gateways unless their reachable action set is fully understood.","Require approval before execution against production systems or sensitive data."]},"risk_type":"runs_code","severity":"high","title":"Imports packages, evaluates snippets and performs browser/mobile actions","triggering_tools":["runner_importPackage","runner_evaluateSnippet","runner_performAction","runner_runFlow"]},{"description":"This connector can navigate pages and interact with browser content on the user's behalf. Review findings: They can act on tested applications.","evidence":"Controls cloud browser/mobile runners: The tools operate interactive browser/device sessions.","manual_risk_type":"browser_control","remediation":{"block_tool_categories":["state_change"],"steps":["Use an isolated browser profile without unrelated authenticated sessions.","Require confirmation before form submission, download, upload, or purchase actions."]},"risk_type":"browser_control","severity":"medium","title":"Controls cloud browser/mobile runners","triggering_tools":["runner_launch","runner_performAction","runner_inspectMobile"]},{"description":"This connector can publish or send messages and content using the connected identity. Review findings: It is user-representative messaging.","evidence":"Sends email and messages to QA agents: Email sends externally as the configured test identity.","manual_risk_type":"messaging_as_user","remediation":{"block_tool_categories":["sends_externally"],"steps":["Require review before messages, posts, or publications are sent.","Restrict delivery to test or internal recipients where possible."]},"risk_type":"sends_messages_as_you","severity":"high","title":"Sends email and messages to QA agents","triggering_tools":["email_send","agent_send"]},{"description":"This connector can create, update, configure, or otherwise change connected resources. Review findings: They are privileged configuration actions.","evidence":"Creates/updates environments and reads/sets variables: These tools administer test environments and potentially secrets.","manual_risk_type":"credential_admin","remediation":{"block_tool_categories":["state_change"],"steps":["Use a test account or sandbox before allowing changes to production data.","Grant only the write permissions required for the intended workflow.","Require human confirmation for consequential state changes."]},"risk_type":"modifies_data","severity":"high","title":"Creates/updates environments and reads/sets variables","triggering_tools":["environment_create","environment_getVariable","environment_setVariable","environment_deleteVariable"]},{"description":"This connector can deploy code or change infrastructure and production environments. Review findings: They launch/stop production QA workloads.","evidence":"Creates/runs/stops/terminates test executions: The tools control cloud test infrastructure.","manual_risk_type":"deployment_infrastructure","remediation":{"block_tool_categories":["code_execution","state_change"],"steps":["Default to a sandbox or staging environment.","Require code review, human approval, audit logging, and a tested rollback path for production changes."]},"risk_type":"code_deployment","severity":"high","title":"Creates/runs/stops/terminates test executions","triggering_tools":["run_create","runner_launch","runner_stopRun","runner_terminate"]}],"signature_status":"unknown","source_code_reviewed":false,"support_url":"support@qawolf.com","tags":["browser_control","code_deployment","modifies_data","network_access","oauth_required","runs_code","sends_messages_as_you","web_connector"],"tools":[{"description":"","name":"agent_get"},{"description":"","name":"agent_send","risk":{"category":"sends_externally","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can publish or send messages and content using the connected identity. Review findings: It is user-representative messaging."}},{"description":"","name":"automate"},{"description":"","name":"email_find"},{"description":"","name":"email_get"},{"description":"","name":"email_getAttachment"},{"description":"","name":"email_listAddresses"},{"description":"","name":"email_send","risk":{"category":"sends_externally","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can publish or send messages and content using the connected identity. Review findings: It is user-representative messaging."}},{"description":"","name":"environment_create","risk":{"category":"state_change","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can create, update, configure, or otherwise change connected resources. Review findings: They are privileged configuration actions."}},{"description":"","name":"environment_deleteVariable","risk":{"category":"state_change","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can create, update, configure, or otherwise change connected resources. Review findings: They are privileged configuration actions."}},{"description":"","name":"environment_find"},{"description":"","name":"environment_get"},{"description":"","name":"environment_getVariable","risk":{"category":"state_change","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can create, update, configure, or otherwise change connected resources. Review findings: They are privileged configuration actions."}},{"description":"","name":"environment_listVariableNames"},{"description":"","name":"environment_setVariable","risk":{"category":"state_change","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can create, update, configure, or otherwise change connected resources. Review findings: They are privileged configuration actions."}},{"description":"","name":"environment_update"},{"description":"","name":"flow_addTag"},{"description":"","name":"flow_list"},{"description":"","name":"flow_removeTag"},{"description":"","name":"flow_update"},{"description":"","name":"issue_addFlows"},{"description":"","name":"issue_create"},{"description":"","name":"issue_find"},{"description":"","name":"issue_get"},{"description":"","name":"issue_removeFlows"},{"description":"","name":"issue_update"},{"description":"","name":"run_create","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can deploy code or change infrastructure and production environments. Review findings: They launch/stop production QA workloads."}},{"description":"","name":"run_diagnose"},{"description":"","name":"run_find"},{"description":"","name":"run_get"},{"description":"","name":"run_reattempt"},{"description":"","name":"runner_evaluateSnippet","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can execute code, commands, queries, or dynamically selected actions. Review findings: They are arbitrary runtime automation."}},{"description":"","name":"runner_get"},{"description":"","name":"runner_highlightSelector"},{"description":"","name":"runner_importPackage","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can execute code, commands, queries, or dynamically selected actions. Review findings: They are arbitrary runtime automation."}},{"description":"","name":"runner_inspect"},{"description":"","name":"runner_inspectMobile","risk":{"category":"state_change","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can navigate pages and interact with browser content on the user's behalf. Review findings: They can act on tested applications."}},{"description":"","name":"runner_launch","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can deploy code or change infrastructure and production environments. Review findings: They launch/stop production QA workloads."}},{"description":"","name":"runner_list"},{"description":"","name":"runner_performAction","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can execute code, commands, queries, or dynamically selected actions. Review findings: They are arbitrary runtime automation."}},{"description":"","name":"runner_promoteSnapshot"},{"description":"","name":"runner_readJournal"},{"description":"","name":"runner_runFlow","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can execute code, commands, queries, or dynamically selected actions. Review findings: They are arbitrary runtime automation."}},{"description":"","name":"runner_stopRun","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can deploy code or change infrastructure and production environments. Review findings: They launch/stop production QA workloads."}},{"description":"","name":"runner_takeScreenshot"},{"description":"","name":"runner_terminate","risk":{"category":"code_execution","level":"high","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can deploy code or change infrastructure and production environments. Review findings: They launch/stop production QA workloads."}},{"description":"","name":"tag_create"},{"description":"","name":"tag_list"},{"description":"","name":"whoami"}],"tools_count":49,"transport":"streamable-http","type":"web_connector","url":"https://claude.ai/directory/b2a5ffae-648b-407d-a8c4-78ce7a35afee","uuid":"b884730b-fd62-5465-a231-a2f9acf60c4a","verification_tier":"community","version":""},"query_key":"qa wolf inc qa wolf","schema_version":1,"status":"match"}