meta-codereview-current-diff
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust, multi-step code review workflow. It follows the principle of least privilege by only reading repository state via
git-diffand does not request or use tools with destructive or network-facing capabilities. - [PROMPT_INJECTION]: The skill ingests untrusted code from Git diffs into LLM prompts (Ingestion point:
read_diffoutput). These inputs are isolated with boundary markers and truncated for safety. However, because the skill has no side-effect capabilities like file-writing or network access (Capability inventory: None), this indirect prompt injection surface is not exploitable and represents no risk to the user's environment.
Audit Metadata