factory-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external issue trackers and pull requests, creating a surface for indirect prompt injection. \n
- Ingestion points: Data retrieved via 'Pull Request Search' and 'Issue Search' in the 'Operating Process' section of SKILL.md. \n
- Boundary markers: Absent. However, the skill includes a constraint to 'never reclassify' items during formatting, which acts as a logical control. \n
- Capability inventory: Read-only access to external trackers via CLI tools (gh, glab). \n
- Sanitization: No explicit content sanitization or escaping is defined. \n- [COMMAND_EXECUTION]: The skill uses official CLI tools like 'gh' and 'glab' for its core functionality of fetching tracker data.
Audit Metadata