rust-code-navigator
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its data ingestion surface.\n
- Ingestion points: The skill reads external Rust source files (e.g., src/main.rs) using the 'Read' tool.\n
- Boundary markers: The skill instructions lack explicit delimiters or specific warnings to ignore instructions embedded within code comments or strings.\n
- Capability inventory: The skill utilizes 'LSP' for code analysis, 'Glob' for file listing, and 'Read' for file content access.\n
- Sanitization: Content retrieved from files is not sanitized or filtered before being processed by the agent.
Audit Metadata