token-lint
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely locally using bundled assets and scripts. It does not perform network requests or access sensitive system directories like SSH or AWS credentials.
- [COMMAND_EXECUTION]: The skill executes a bundled script (
scripts/lint.mjs) using Node.js to scan user-specified paths for token usage. The script uses built-in Node.js modules for file system access and excludes sensitive project directories. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external files. 1. Ingestion points: The script reads files at the user-provided path in
scripts/lint.mjs. 2. Boundary markers: The agent is instructed to relay the tool's output verbatim, acting as a functional boundary. 3. Capability inventory: The skill can read files and output content but lacks network or file-write capabilities. 4. Sanitization: Token names are extracted using a restrictive regex (VAR_RE) that only permits alphanumeric characters, underscores, and dashes.
Audit Metadata