oss-hygiene
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from target repositories during its audit and configuration phase.
- Ingestion points: The skill reads existing workflow files located in
.github/workflows/and consumes repository metadata viagh repo view. - Boundary markers: The protocol does not specify the use of clear delimiters or instructions to ignore embedded commands when the agent reads external file content.
- Capability inventory: The skill has the capability to write new files to the repository and modify sensitive repository settings (such as secret scanning and vulnerability reporting) via the GitHub CLI.
- Sanitization: There is no documentation of specific sanitization, filtering, or validation logic applied to the content of existing files being audited.
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI to interact with and modify the state of the target repository.
- Evidence: The protocol explicitly uses commands including
gh repo view,gh api(GET/PATCH/PUT/X), andlsto verify status and enable security features.
Audit Metadata