axum-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code, which creates a vulnerability surface for indirect prompt injection if those files contain malicious instructions meant to subvert the agent's behavior. * Ingestion points: The skill instructs the agent to read Cargo.toml and Rust source files from the current project tree as specified in the Review Workflow and Gates. * Boundary markers: Findings must cite specific [FILE:LINE] locations, providing context, but the skill lacks explicit instructions or delimiters to ignore potential prompts embedded in the analyzed source code. * Capability inventory: The skill itself contains no scripts or executables, but it is intended for use by agents that typically possess file system and command execution capabilities. * Sanitization: There is no sanitization, filtering, or strict schema validation for the source code data being reviewed.
Audit Metadata