clean-pro-review-gates
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze untrusted external data (such as source code, git diffs, and pull request information), creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The 'Standard 5-Gate Review Process' in
SKILL.mdexplicitly defines ingestion points for external data via commands likegit diff main...HEADand the analysis of PR file lists. - Boundary markers: The instructions do not define specific syntactic delimiters or 'ignore' instructions for the agent to separate the input data from the review logic, which increases the risk of the agent obeying instructions embedded within the code being reviewed.
- Capability inventory: The skill utilizes the agent's core capabilities to read repository files and generate textual reports. It does not perform automated file modifications or network operations based on the input data.
- Sanitization: No explicit sanitization or filtering of the ingested code is performed; the skill relies on the agent's strict adherence to the defined 'Imperatives' (e.g., in
references/security-review-gate.md) to mitigate influence from the processed content. - [NO_CODE]: The skill consists entirely of Markdown documentation, YAML configuration, and a JSON test suite. It contains no executable scripts, binaries, or active code components.
Audit Metadata