code-review
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for code review best practices. No executable code, shell commands, or network operations were found.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted data (code diffs and review comments). While this constitutes an ingestion surface, the skill lacks any capabilities—such as file writes, network requests, or tool invocations—that could be exploited by an injection attack.
- [NO_CODE]: There are no scripts, dependencies, or metadata fields that introduce security risks.
Audit Metadata