github-fix-issue
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data from GitHub issues (titles, bodies, and comments) using the
gh issue viewcommand. This represents a potential attack surface for indirect prompt injection where an issue could contain malicious instructions designed to manipulate the agent. - Ingestion points: GitHub issue content fetched via
gh issue view(SKILL.md). - Boundary markers: The skill includes a robust security warning instructing the agent to treat all issue content as untrusted data and to ignore any instructions addressed to the agent or subagents (SKILL.md).
- Capability inventory: The skill uses file manipulation (Read, Write, Edit) and shell commands (gh, git) to implement fixes and submit PRs (SKILL.md).
- Sanitization: The skill relies on natural language instructions to steer the agent away from obeying embedded commands rather than programmatic sanitization.
Audit Metadata