pr-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of pull request diffs and source code files. This creates a potential surface for indirect prompt injection if an attacker embeds malicious instructions within code comments or documentation in the PR being reviewed.
- Ingestion points: Step 2 of the workflow requires fetching the "full file context" and diffs of changed files.
- Boundary markers: The instructions do not mandate the use of XML tags or specific delimiters to isolate the code being reviewed from the agent's core instructions.
- Capability inventory: The skill itself defines no tools, but the workflow implies the agent utilizes file-reading capabilities to perform the review.
- Sanitization: No explicit sanitization or instruction-filtering for the ingested code is provided.
- [SAFE]: The skill consists entirely of markdown instructions and does not include scripts, binary files, or package dependencies. The source URL provided in the metadata points to the maintainer's official repository.
Audit Metadata