review-learning-repo-pr
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or safety violations were detected. The skill defines a standard pull request review process using local tools.
- [COMMAND_EXECUTION]: The skill executes a local shell script (
scripts/list-learning-files.sh) to identify modified files. This script uses standard git commands (git diff) and does not perform network operations or access sensitive system files. - [PROMPT_INJECTION]: The skill is designed to review pull request content, which constitutes untrusted external data. This creates a potential surface for indirect prompt injection. 1. Ingestion points: Modified repository files (e.g., README.md, skills/) listed via git diff. 2. Boundary markers: Absent; the instructions do not specify delimiters to separate untrusted data from the review checklist. 3. Capability inventory: The agent utilizes file reading capabilities to perform the review. 4. Sanitization: Absent.
Audit Metadata