review-agent
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Potential Surface for Indirect Prompt Injection]: The agent is instructed to read and analyze external code changes and documentation (such as
AGENTS.md). Content within these sources could potentially contain instructions intended to influence the agent's behavior or findings. - Ingestion points: Code changes, diffs, and the
AGENTS.mdfile are read as specified inSKILL.md. - Boundary markers: No specific delimiters or boundary markers are defined to separate the code content from the agent's primary instructions.
- Capability inventory: The skill involves executing local
gitcommands (git merge-base,git diff) inSKILL.mdto perform version comparison. - Sanitization: No specific sanitization or filtering of the code content is mentioned prior to analysis.
Audit Metadata