github-codeowners-management
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for repository configuration management. It includes a Python script (scripts/lint_codeowners.py) that performs static analysis on local CODEOWNERS files to ensure compliance with ownership policies. The script does not utilize network operations, dynamic code execution, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill has a theoretical surface for indirect prompt injection. 1. Ingestion points: The linting script reads content from user-specified local files. 2. Boundary markers: There are no explicit delimiters or warnings to ignore embedded instructions in the prompt. 3. Capability inventory: The skill allows creating plan templates and linting files. 4. Sanitization: No sanitization is performed on the file content before processing. However, the risk is negligible as the script performs structural validation and does not interpret the content as instructions.
Audit Metadata