rust-code-navigator
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) as it processes untrusted data from the local codebase.
- Ingestion points: The workflow involves reading local Rust files (e.g.,
src/main.rs,src/config.rs) and LSP symbols to display code context to the user. - Boundary markers: Absent. There are no delimiters or 'ignore' instructions used when interpolating file content into the agent's context.
- Capability inventory: The skill utilizes
LSP,Read, andGlob, which grant the agent permissions to access and read the entire workspace directory. - Sanitization: Absent. The skill passes code comments and documentation directly to the LLM, which could contain malicious instructions.
- EXTERNAL_DOWNLOADS (LOW): The skill recommends external software installation through trusted channels.
- Evidence: The 'Error Handling' section suggests the command
rustup component add rust-analyzer. Althoughrustupis a trusted source, the action involves downloading and installing external binaries, which warrants a LOW severity under the [TRUST-SCOPE-RULE].
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata