skill-validator
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a static analysis tool, reading and validating local file content without executing it. It uses regular expressions to identify potential issues in other files.
- [SAFE]: Mentions of security-sensitive commands like 'eval' or 'exec' in the source code are used purely for detection logic within the validator script, not for dynamic execution.
- [SAFE]: Recommendations to install external dependencies such as 'pyyaml' refer to well-known, legitimate libraries from standard package registries.
- [SAFE]: The skill inherently processes untrusted data as its primary function (Category 8: Indirect Prompt Injection surface), but as a linter, it does not execute the data it ingests. Evidence Chain: 1. Ingestion points: Target skill directory (SKILL.md, scripts/); 2. Boundary markers: Absent in report output; 3. Capability inventory: Local file read and directory traversal in 'validate_skill.py'; 4. Sanitization: Absent (extracted data is printed as-is in the report). The risk is considered negligible given the skill's purpose.
Audit Metadata