rust-symbol-analyzer

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted content from local Rust files to extract symbols and structure. Ingestion points: File discovery via Glob and metadata extraction via LSP. Boundary markers: Absent. Capability inventory: LSP, Read, Glob. Sanitization: Absent. Malicious instructions embedded in code comments or strings could potentially influence the agent's summary or reasoning.
  • Information (INFO): A third-party scanner flagged main.rs as a malicious URL. This is identified as a false positive where the Rust source file name was misinterpreted as a domain using the Serbian (.rs) top-level domain. The skill correctly references this as a local file path.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:02 AM