issue-fix-flow
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from GitHub issues, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The command
gh issue view <id> --commentsinSKILL.mdimports external issue content directly into the agent's processing context. - Boundary markers: The instructions do not specify any delimiters or warnings to treat issue content as data only, increasing the risk that the agent may interpret embedded text as instructions.
- Capability inventory: The skill environment allows for code execution via build tools like
swift buildandxcodebuild, and repository modification and data transmission viagit pushandgh pr create. - Sanitization: There are no documented steps for sanitizing or validating the content retrieved from GitHub before it is processed by the agent.
Audit Metadata