pr-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data in the form of code diffs from Git and GitHub PRs.
- Ingestion points: The workflow involves executing
git diffandgh pr diffto retrieve code changes, and reading the project'sCLAUDE.mdand source files (Phase 1 and Phase 2 inSKILL.md). - Boundary markers: There are no specific instructions to use delimiters or ignore instructions embedded within the code being reviewed to prevent the agent from following instructions hidden in comments or strings in the diff.
- Capability inventory: The agent uses tools to read files and execute git/gh commands. It does not have access to arbitrary network writes or dangerous dynamic execution tools (like
eval) in its described workflow. - Sanitization: The skill does not explicitly describe sanitization or filtering of the diff content before it is processed by the AI.
Audit Metadata