github
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from GitHub (issues, pull requests, and repository files), which serves as an ingestion point for potentially untrusted data that could attempt to influence the agent's behavior.
- Ingestion points: Data fetched via
github call-read-toolfrom external GitHub repositories. - Boundary markers: No explicit delimiters or specialized parsing instructions for tool outputs are defined in the skill instructions.
- Capability inventory: The skill possesses both read and write capabilities (
mcp.read,mcp.write). Write actions require fresh user consent (fresh_consent_only). - Sanitization: The local binary implements a reviewed allowlist for read tools, and the platform enforces approval policies for write operations to mitigate risks.
Audit Metadata