axum-code-review

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill mandates that the agent 'Load and follow beagle-rust:review-verification-protocol' before providing findings, creating a multi-step instruction chain (Category 8b) where behavior depends on an external resource. 1. Ingestion points: The skill processes user-supplied Rust code and the referenced protocol. 2. Boundary markers: No markers or delimiters are defined to isolate the reviewed code or the external protocol instructions. 3. Capability inventory: The skill contains no code of its own but utilizes the agent's built-in file reading and analysis capabilities. 4. Sanitization: No sanitization or validation of the external protocol content is performed.
  • [NO_CODE]: The skill package contains only Markdown documentation and reference guides. No executable scripts, binary files, or dependency manifests (e.g., package.json or requirements.txt) are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:29 AM