review-tests
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates external code files, creating a surface for indirect prompt injection where malicious instructions within the code could potentially influence the agent's behavior. \n
- Ingestion points: Test files identified by git diff commands in SKILL.md. \n
- Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded prompts. \n
- Capability inventory: Local command execution via git and implicit file reading. \n
- Sanitization: Absent. No sanitization or validation of the code input is mentioned. \n- [COMMAND_EXECUTION]: The skill uses shell commands to automate the detection of files requiring review. \n
- Evidence: Bash snippets in SKILL.md demonstrate the use of
git diffandgit symbolic-ref.
Audit Metadata