pr-multi-perspective-review
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub Pull Request titles, descriptions, and code diffs which could potentially contain malicious instructions intended to influence the agent's review output.
- Ingestion points: PR metadata and code diffs are ingested using the
gh pr viewandgh pr diffcommands in SKILL.md. - Boundary markers: The instructions do not specify the use of clear delimiters or explicit 'ignore embedded instructions' warnings for the agent when processing raw PR data.
- Capability inventory: The agent has access to the GitHub CLI (
gh) and MCP tools for reading repository data and can post findings usinggh pr comment. - Sanitization: The skill does not provide specific guidance on sanitizing or escaping the content of the PR before the agent evaluates it.
- [EXTERNAL_DOWNLOADS]: The skill references a community resource repository on GitHub (
github.com/hesreallyhim/awesome-claude-code) for documentation and inspiration. This is a reference to a well-known service.
Audit Metadata