yzr-coding-review
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate development tool for code analysis. It does not perform network operations, exfiltrate data, or access sensitive credentials. Its operations are limited to reading code and providing dialogue-based recommendations.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it ingests untrusted code blocks and files for analysis. 1. Ingestion points: Code snippets, file paths, and git diffs as specified in SKILL.md (Step 1). 2. Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore instructions embedded within the code being reviewed. 3. Capability inventory: The skill utilizes file reading tools and has the potential to modify project files if the user accepts a refactoring suggestion. 4. Sanitization: No input sanitization or filtering is implemented for the code provided to the agent. The risk is mitigated by the skill's core principle of requiring explicit user approval before any file system modifications are executed.
Audit Metadata