unsafe-checker
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an educational and procedural guide for Rust code audits. It contains no executable scripts, network operations, or persistence mechanisms.
- [PROMPT_INJECTION]: Metadata fields use labels like 'CRITICAL' for classification, and instructions include directives for specific content display. These are instructional reinforcements consistent with a specialized auditor role and do not attempt to bypass safety guardrails.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for its use case as it analyzes untrusted source code. 1. Ingestion points: Rust source files (**/*.rs) processed by the agent. 2. Boundary markers: No explicit markers or 'ignore' instructions are provided to separate analyzed code from instructions. 3. Capability inventory: The agent is permitted to use 'Read', 'Grep', and 'Glob' tools. 4. Sanitization: No instructions are given to sanitize or validate the content of the files being reviewed.
Audit Metadata