{"generated_at":"2026-10-14T20:07:22+00:00","item":{"added_at":"2026-08-20","analysis_method":"independent_manual_review_2026-10-10","assessment_status":"provisional","auth_posture":"auth_required","category":"Web Connector","confidence":"medium","description":"Cotera lets Claude browse, create, and run agents in an authenticated workspace. Search connected tools and documents, inspect agent prompts, and create new agents from Markdown instructions. Run a single input or up to 50 parallel inputs, then collect background results.","did":"554598c1-bad2-4d81-b68e-193cfdd2e668","documentation_url":"https://cotera.co/docs","editorial_description":{"extended_description":"Created agents remain ordinary Cotera workspace agents that the team can edit, schedule, and share in the app. Tool and document search helps reference available workspace resources, and existing agents can be listed and read.","schema_version":1,"summary":"Cotera lets Claude browse, create, and run agents in an authenticated workspace.\nSearch connected tools and documents, inspect agent prompts, and create new agents from Markdown instructions.\nRun a single input or up to 50 parallel inputs, then collect background results."},"homepage_url":"","icon":"","id":"554598c1-bad2-4d81-b68e-193cfdd2e668","installs":0,"last_scanned":"","license":"","long_description":"Created agents remain ordinary Cotera workspace agents that the team can edit, schedule, and share in the app. Tool and document search helps reference available workspace resources, and existing agents can be listed and read.","manual_assessment":"high","manual_review":{"all_findings":[{"evidence":"Tools execute configured agents, possibly in batch.","reasoning":"Agent execution is High.","risk_type":"code_execution","severity":"high","title":"Runs user-defined agents","triggering_tools_or_skills":["run_agent","batch_run_agent"]},{"evidence":"Description says agents reference connected tools; reachable actions are not enumerated.","reasoning":"Hidden actions may include arbitrary High capabilities.","risk_type":"generic_gateway","severity":"high","title":"Agents can call dynamically searched tools","triggering_tools_or_skills":["search_tools","create_agent_from_prompt","run_agent"]},{"evidence":"Tool creates an agent in the workspace.","reasoning":"Persistent configuration is Medium.","risk_type":"data_modification","severity":"medium","title":"Creates persistent agents","triggering_tools_or_skills":["create_agent_from_prompt"]},{"evidence":"Remote hosted implementation is unpinned.","reasoning":"Runtime capabilities can drift.","risk_type":"provenance_uncertainty","severity":"low","title":"Hosted implementation is mutable","triggering_tools_or_skills":[]}],"assessment_status":"provisional","auth_and_scopes":"OAuth/account authorization required; exact scopes are not documented.","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/554598c1-bad2-4d81-b68e-193cfdd2e668.json","what_it_proves":"Candidate PR #125 record identity (name \"app.cotera.co\", publisher, type web_connector) and 8 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/554598c1-bad2-4d81-b68e-193cfdd2e668: complete tool_names inventory (8 tools), remote streamable-http endpoint https://app.cotera.co/mcp, auth_posture auth_required, directory tier community"}],"primary_reason":"Cotera creates and executes agents that can use dynamically discovered connected tools.","provisional_risk":null,"publication_recommendation":"fix","requires_runtime_verification":true,"review_key":"claude:554598c1-bad2-4d81-b68e-193cfdd2e668","reviewed_at":"2026-10-10","reviewer_notes":"All declared tool names were reviewed; schemas were not available.","risk_domains":{"arbitrary_network_access":"false","authz_ambiguity":"unknown","browser_control":"false","credential_or_admin_actions":"false","deletes_data":"false","deployment_or_infrastructure":"false","dynamic_hidden_actions":"true","filesystem_or_repo_access":"false","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":"false","spends_or_moves_money":"false"},"tools_or_skills_reviewed":8,"tools_or_skills_total":8},"name":"app.cotera.co","needs_runtime_verification":true,"plutonium_url":"https://plutonium.pluto.security/detail.html?planet=claudesec&did=554598c1-bad2-4d81-b68e-193cfdd2e668&utm_source=plutonium_analysis_skill&utm_medium=claude_skill&utm_campaign=connector_risk_assessment","privacy_policy_url":"https://cotera.co/legal/privacy","provisional_risk":null,"publication_recommendation":"fix","publisher":"Cotera","publisher_url":"https://cotera.co/","remote_url":"https://app.cotera.co/mcp","repository_url":"","risk":"high","risk_severity":"high","security_risks":[{"description":"This connector can execute code, commands, queries, or dynamically selected actions. Review findings: Agent execution is High.; Hidden actions may include arbitrary High capabilities.","evidence":"Runs user-defined agents: Tools execute configured agents, possibly in batch. | Agents can call dynamically searched tools: Description says agents reference connected tools; reachable actions are not enumerated.","manual_risk_type":"code_execution,generic_gateway","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":"Can execute code, queries, or dynamic actions","triggering_tools":["run_agent","batch_run_agent","search_tools","create_agent_from_prompt"]},{"description":"This connector can create, update, configure, or otherwise change connected resources. Review findings: Persistent configuration is Medium.","evidence":"Creates persistent agents: Tool creates an agent in the workspace.","manual_risk_type":"data_modification","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":"medium","title":"Creates persistent agents","triggering_tools":["create_agent_from_prompt"]}],"signature_status":"unknown","source_code_reviewed":false,"support_url":"support@cotera.co","tags":["modifies_data","network_access","oauth_required","runs_code","web_connector"],"tools":[{"description":"","name":"batch_run_agent","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: Agent execution is High.; Hidden actions may include arbitrary High capabilities."}},{"description":"","name":"create_agent_from_prompt","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: Agent execution is High.; Hidden actions may include arbitrary High capabilities."}},{"description":"","name":"get_agent"},{"description":"","name":"get_run_results"},{"description":"","name":"list_agents"},{"description":"","name":"run_agent","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: Agent execution is High.; Hidden actions may include arbitrary High capabilities."}},{"description":"","name":"search_documents"},{"description":"","name":"search_tools","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: Agent execution is High.; Hidden actions may include arbitrary High capabilities."}}],"tools_count":8,"transport":"streamable-http","type":"web_connector","url":"https://claude.ai/directory/554598c1-bad2-4d81-b68e-193cfdd2e668","uuid":"365c2040-c1e9-5d11-94dc-207820dee984","verification_tier":"community","version":""},"query_key":"cotera app cotera co","schema_version":1,"status":"match"}