github-repo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub repositories, creating a surface for indirect prompt injection.
- Ingestion Point:
scripts/audit-repo.shfetches and decodes repository README files and other metadata via the GitHub API. - Boundary Markers: The skill does not use specific delimiters or instructions to prevent the agent from accidentally following instructions that might be embedded within a repository's documentation.
- Capability Inventory: While the audit script is read-only, the skill directs the agent to interpret findings and generate repair suggestions based on the repository content.
- Sanitization: No sanitization or safety-filtering is applied to the repository content before it is presented to the agent for analysis.
Audit Metadata