github
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill retrieves and processes untrusted content from GitHub repositories, which could contain malicious instructions targeting the AI agent.\n
- Ingestion points: Untrusted data is retrieved via
gh api,gh issue list, andgh run viewas shown in SKILL.md.\n - Boundary markers: The instructions do not define delimiters or provide warnings to the agent to disregard instructions embedded within the fetched data.\n
- Capability inventory: The skill uses the
ghCLI, which allows the agent to read and modify data on GitHub.\n - Sanitization: The skill uses
jqto filter JSON fields but does not sanitize the textual content of those fields before it is processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill requires the official GitHub CLI (gh), which is installed via well-known and trusted package managers (brew, apt).
Audit Metadata