qa
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided bug reports and incorporates them into GitHub issue templates which are then processed by the
gh issue createcommand. - Ingestion points: Untrusted user input enters the agent context through conversational problem descriptions in the 'Listen and lightly clarify' section of SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands when processing the user's description.
- Capability inventory: The skill utilizes the GitHub CLI (
gh issue create) to perform write operations to external repositories. - Sanitization: There are no instructions to sanitize or escape the user-provided text before it is inserted into the markdown templates used for issue creation.
Audit Metadata