review-code
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, including git diffs, commit logs, and specification files (e.g., feature tickets, ADRs), which serves as a primary ingestion point for potentially malicious instructions.
- Ingestion Points: Ingestion occurs through
git diff,git log, and external specification documents as described inreferences/process-and-format.md. - Capability Inventory: The skill is granted access to high-privilege tools in
SKILL.md, includingexecute_command,run_build,run_tests,write_file, andedit_file. - Boundary Markers: While the skill uses parallel sub-agents to separate the 'Standards' and 'Spec' review axes, it lacks explicit delimiters or instructions to ignore potential commands embedded within the code or specifications being reviewed.
- Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the agent or sub-agents.
Audit Metadata