qa-linear-integration

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text from bug reports and task descriptions to populate fields in Linear issues.
  • Ingestion points: Bug report and task data provided by the qa-bug-ticket-creator and qa-task-creator skills (SKILL.md).
  • Boundary markers: The skill lacks explicit boundary delimiters or instructions to ignore potential commands within the interpolated description fields.
  • Capability inventory: External write capabilities via GraphQL mutations (issueCreate, issueUpdate) directed to the Linear API.
  • Sanitization: No sanitization or validation protocols are defined for the input text prior to its inclusion in API payloads.
  • [EXTERNAL_DOWNLOADS]: The skill references and interacts with the official Linear service API.
  • The skill communicates with the official Linear GraphQL endpoint at https://api.linear.app/graphql.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:39 PM
Security Audit — agent-trust-hub — qa-linear-integration