code-review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted content from GitHub Pull Requests, which presents an indirect prompt injection surface.
- Ingestion points: Pull Request diffs, file contents, and dependency manifests as described in the review criteria in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or warnings to the agent to explicitly disregard instructions found within the code being reviewed.
- Capability inventory: The skill consists of Markdown instructions and reference material; it does not include or request access to executable scripts, shell commands, or network-enabled tools.
- Sanitization: No specific sanitization or validation of the PR content is requested before analysis.
Audit Metadata