to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior during the ticket generation process.\n
- Ingestion points: The skill fetches and reads full bodies and comments from tracker URLs, local issues folders, and project PRD paths as specified by the user or project context.\n
- Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore embedded instructions within the fetched specification data.\n
- Capability inventory: The agent has the ability to explore the codebase (file system read), write local files to the
.scratch/directory, and publish issues to external trackers like GitHub or Linear (network write).\n - Sanitization: There are no procedures defined in the skill instructions to sanitize or validate the content of the ingested specifications before the agent uses them to draft vertical slices.
Audit Metadata