sync-github-repo-metadata
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data such as repository source code, READMEs, and documentation to generate metadata updates. This data could contain malicious instructions intended to manipulate the agent's summary or the resulting shell commands.\n
- Ingestion points: Reads repository facts, README, and documentation as specified in SKILL.md.\n
- Boundary markers: The instructions do not specify delimiters or techniques to ignore embedded commands within the analyzed files.\n
- Capability inventory: Executes gh repo view and gh repo edit commands as described in SKILL.md.\n
- Sanitization: The skill includes a manual preview and confirmation step before executing the final command, providing a human-in-the-loop check.\n- [COMMAND_EXECUTION]: The skill generates and executes gh repo edit commands based on inferred metadata. While this is the intended functionality, it involves running shell commands derived from external, potentially untrusted repo content, which requires careful user review.
Audit Metadata