youtrack

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes data from external YouTrack tickets and possesses significant write capabilities.
  • Ingestion points: Ticket details are retrieved from the YouTrack API via the get-ticket.ts script.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ensure the agent ignores instructions potentially embedded in the ticket description or comments.
  • Capability inventory: The skill provides tools to add comments, manage tags, update ticket statuses, and manage release versions (including deletion).
  • Sanitization: There is no mention of sanitizing or validating retrieved ticket content before it enters the agent's context.
  • [PROMPT_INJECTION]: The skill contains metadata poisoning (Category 7) through the inclusion of a skill-report.json file that makes authoritative claims about the skill's own security risk level and safety.
  • [COMMAND_EXECUTION]: The skill documents the execution of repository-local TypeScript tools using npx tsx to perform all issue tracker operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 11:35 PM
Security Audit — agent-trust-hub — youtrack