linear-enterprise-rbac

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements logic to ingest and process user metadata from the Linear API, which represents an attack surface for instructions embedded in external data.
  • Ingestion points: External user data is fetched via the Linear GraphQL API in references/implementation.md (via list_workspace_members) and SKILL.md (via syncSCIMUsers).
  • Boundary markers: There are no identified delimiters or explicit instructions provided to the model to ignore potential instructions embedded within the retrieved API fields (e.g., names, emails).
  • Capability inventory: The skill provides code for high-privilege actions, including user demotion (userUpdate mutation) and issue modification (createIssue, updateIssue).
  • Sanitization: The implementation patterns do not include sanitization or validation of external string data before it is logged or stored in the database.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 08:05 PM
Security Audit — agent-trust-hub — linear-enterprise-rbac