code-review-md
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code through git diffs, which provides a potential surface for indirect prompt injection attacks where malicious code could attempt to influence the agent's analysis.
- Ingestion points: Code changes are ingested via
git diffas described in the workflow section of SKILL.md. - Boundary markers: The skill references an 'Evidence-first writing contract' and specific report templates defined in the parent
code-reviewskill to structure the output. - Capability inventory: The skill can execute shell commands (
git diff,diff_stats.py) and write files to the.reviews/directory. - Sanitization: The instructions do not specify explicit sanitization or filtering of the diff content before it is processed by the model.
- [COMMAND_EXECUTION]: The workflow requires the execution of local shell commands and scripts to perform its primary function.
- Evidence: The skill instructs the agent to run
git diffand a local script nameddiff_stats.pyto gather data for the review report.
Audit Metadata