code-review-master
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local bash script
scripts/pr-diff.shthat utilizesgh(GitHub CLI) andjqto retrieve pull request information and code diffs from external repositories. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection from processed data.
- Ingestion points: Untrusted data enters the agent context through the
scripts/pr-diff.shscript, which fetches pull request titles, bodies, and source code diffs. - Boundary markers: While the script wraps retrieved content in Markdown code blocks, there are no specific instructions to the AI model to ignore embedded natural language commands within the processed data.
- Capability inventory: The skill conducts security and logic analysis based on the ingested content. It does not possess direct file-write or network-send capabilities beyond the read-only fetch operations.
- Sanitization: The script uses
jqto ensure structural data integrity for JSON output, but it does not perform filtering or sanitization of natural language instructions present in the ingested content.
Audit Metadata