to-tickets
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill references an external configuration command,
/setup-utarn-skills, to initialize tracking settings and issue tracker credentials. \n- [DATA_EXFILTRATION]: The skill's primary function includes transmitting ticket details to configured external services like GitHub or Linear. This data transfer is a core feature but is subject to a mandatory user review and approval process. \n- [PROMPT_INJECTION]: The skill ingests untrusted data from external project documents, creating a surface for indirect prompt injection. \n - Ingestion points: Fetches and reads external specifications, issue bodies, and comments as described in the context gathering section of SKILL.md. \n
- Boundary markers: There are no explicit instructions or delimiters used to isolate external content from the agent's internal logic. \n
- Capability inventory: Includes local file writing to the .scratch directory and the ability to publish tickets via tracker APIs. \n
- Sanitization: No automated sanitization is implemented; the risk is managed through a mandatory human-in-the-loop review step where the user validates all proposed tickets before publication.
Audit Metadata