{"generated_at":"2026-10-14T20:07:22+00:00","item":{"added_at":"2026-07-01","analysis_method":"independent_manual_review_2026-10-10","assessment_status":"provisional","auth_posture":"auth_required","category":"Web Connector","confidence":"medium","description":"Norrsent connects enterprise risk and governance records to Claude. Inspect risks, controls, indicators, mitigations, incidents, and policies. Update risks or report incidents within your role-based permissions.","did":"f24e716e-9fe7-478b-a51f-3551dca7643d","documentation_url":"https://www.norrsent.com/docs/mcp-connector","editorial_description":{"extended_description":"Review organizational structure, policy reviews, incident statistics, and the aggregated risk matrix. Access activity is recorded in an audit log.","schema_version":1,"summary":"Norrsent connects enterprise risk and governance records to Claude.\nInspect risks, controls, indicators, mitigations, incidents, and policies.\nUpdate risks or report incidents within your role-based permissions."},"homepage_url":"","icon":"","id":"f24e716e-9fe7-478b-a51f-3551dca7643d","installs":0,"last_scanned":"","license":"","long_description":"Review organizational structure, policy reviews, incident statistics, and the aggregated risk matrix. Access activity is recorded in an audit log.","manual_assessment":"medium","manual_review":{"all_findings":[{"evidence":"The connector explicitly updates a risk record and creates an incident in the ERM/GRC workspace.","reasoning":"These actions alter formal governance and incident records that may drive response or reporting.","risk_type":"data_modification","severity":"medium","title":"Risks can be updated and incidents reported","triggering_tools_or_skills":["update_risk","create_incident"]},{"evidence":"The listing provides the risk register, controls/effectiveness, KRIs, mitigations, active threats, policies, incidents, and organizational hierarchy.","reasoning":"This is sensitive enterprise security, governance, and organizational data.","risk_type":"private_data_read","severity":"medium","title":"Enterprise risks, controls, policies, threats, and incidents are exposed","triggering_tools_or_skills":["list_risks","list_controls","list_policies","list_threats","list_incidents","company_tree"]},{"evidence":"User-authored incident, policy, mitigation, and risk narratives are retrieved.","reasoning":"Workspace text is untrusted and may contain embedded instructions.","risk_type":"prompt_injection_exposure","severity":"low","title":"Incident and policy text enters context","triggering_tools_or_skills":["get_incident","get_policy","get_risk"]}],"assessment_status":"provisional","auth_and_scopes":"Authentication scopes Norrsent actions to existing role-based permissions and audit logging according to the listing; exact roles are not enumerated.","blocked_missing_evidence":null,"confidence":"medium","displayed_risk":"medium","evidence_completeness":"partial","manual_overall_risk":"medium","official_sources":[{"accessed_at":"2026-10-10T20:24:37Z","url_or_path":"plutosecurity/plutonium@b749c8dc43536c794409be9805edd48063f045e2:app/data/conn/claudesec/f24e716e-9fe7-478b-a51f-3551dca7643d.json","what_it_proves":"Candidate PR #125 record identity (name \"Norrsent - Agentic Risk Management & GRC\", publisher, type web_connector) and 16 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/f24e716e-9fe7-478b-a51f-3551dca7643d: complete tool_names inventory (16 tools), remote streamable-http endpoint https://api.norrsent.com/mcp, auth_posture auth_required, directory tier community"}],"primary_reason":"Norrsent reads sensitive GRC data and can update risks or report incidents.","provisional_risk":null,"publication_recommendation":"accept","requires_runtime_verification":true,"review_key":"claude:f24e716e-9fe7-478b-a51f-3551dca7643d","reviewed_at":"2026-10-10","reviewer_notes":"Reviewed all 16 tools; no delete, policy approval, messaging, or user administration is declared.","risk_domains":{"arbitrary_network_access":"false","authz_ambiguity":"false","browser_control":"false","credential_or_admin_actions":"false","deletes_data":"false","deployment_or_infrastructure":"false","dynamic_hidden_actions":"false","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":"false","sends_messages_as_user":"false","spends_or_moves_money":"false"},"tools_or_skills_reviewed":16,"tools_or_skills_total":16},"name":"Norrsent - Agentic Risk Management & GRC","needs_runtime_verification":true,"plutonium_url":"https://plutonium.pluto.security/detail.html?planet=claudesec&did=f24e716e-9fe7-478b-a51f-3551dca7643d&utm_source=plutonium_analysis_skill&utm_medium=claude_skill&utm_campaign=connector_risk_assessment","privacy_policy_url":"https://www.norrsent.com/privacy","provisional_risk":null,"publication_recommendation":"accept","publisher":"Norrsent","publisher_url":"https://www.norrsent.com/","remote_url":"https://api.norrsent.com/mcp","repository_url":"","risk":"medium","risk_severity":"medium","security_risks":[{"description":"This connector can create, update, configure, or otherwise change connected resources. Review findings: These actions alter formal governance and incident records that may drive response or reporting.","evidence":"Risks can be updated and incidents reported: The connector explicitly updates a risk record and creates an incident in the ERM/GRC 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":"Risks can be updated and incidents reported","triggering_tools":["update_risk","create_incident"]},{"description":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data.","evidence":"Enterprise risks, controls, policies, threats, and incidents are exposed: The listing provides the risk register, controls/effectiveness, KRIs, mitigations, active threats, policies, incidents, and organizational hierarchy.","manual_risk_type":"private_data_read","remediation":{"block_tool_categories":["data_exfiltration"],"steps":["Use a least-privilege account limited to the information required by the workflow.","Restrict folders, projects, tenants, and other data scopes wherever the provider allows it.","Review access logs for unexpected reads or bulk retrieval."]},"risk_type":"reads_private_data","severity":"medium","title":"Enterprise risks, controls, policies, threats, and incidents are exposed","triggering_tools":["list_risks","list_controls","list_policies","list_threats","list_incidents","company_tree"]}],"signature_status":"unknown","source_code_reviewed":false,"support_url":"support@norrsent.com","tags":["modifies_data","network_access","oauth_required","reads_private_data","web_connector"],"tools":[{"description":"","name":"company_tree","risk":{"category":"data_exfiltration","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data."}},{"description":"","name":"create_incident","risk":{"category":"state_change","level":"medium","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: These actions alter formal governance and incident records that may drive response or reporting."}},{"description":"","name":"get_enterprise_matrix"},{"description":"","name":"get_incident"},{"description":"","name":"get_incident_stats"},{"description":"","name":"get_policy"},{"description":"","name":"get_risk"},{"description":"","name":"list_controls","risk":{"category":"data_exfiltration","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data."}},{"description":"","name":"list_incidents","risk":{"category":"data_exfiltration","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data."}},{"description":"","name":"list_kris"},{"description":"","name":"list_mitigations"},{"description":"","name":"list_policies","risk":{"category":"data_exfiltration","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data."}},{"description":"","name":"list_policy_reviews"},{"description":"","name":"list_risks","risk":{"category":"data_exfiltration","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data."}},{"description":"","name":"list_threats","risk":{"category":"data_exfiltration","level":"medium","recommendation":"Follow the connector-level remediation and require approval for consequential actions.","why":"This connector can read information available to the connected account and return it to the AI. Review findings: This is sensitive enterprise security, governance, and organizational data."}},{"description":"","name":"update_risk","risk":{"category":"state_change","level":"medium","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: These actions alter formal governance and incident records that may drive response or reporting."}}],"tools_count":16,"transport":"streamable-http","type":"web_connector","url":"https://claude.ai/directory/f24e716e-9fe7-478b-a51f-3551dca7643d","uuid":"555c2780-0a96-5941-9331-115f5eae9dea","verification_tier":"community","version":""},"query_key":"norrsent agentic risk management grc","schema_version":1,"status":"match"}