type-safety-audit
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or reference files.
- [COMMAND_EXECUTION]: The skill uses the shell 'find' command to discover TypeScript files for analysis. This is a standard operation for a code auditing tool.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and validation libraries from established domains including typescriptlang.org, zod.dev, and github.com (io-ts). These references are used for educational purposes and do not involve runtime code execution.
- [PROMPT_INJECTION]: The skill processes untrusted TypeScript files from the local filesystem (Indirect Prompt Injection surface).
- Ingestion points: The skill reads all .ts files found in the project directory (SKILL.md, Step 2).
- Boundary markers: None identified.
- Capability inventory: Includes file discovery via 'find' and file reading. No execution of audited code content (exec/eval) is performed.
- Sanitization: Not applicable, as the skill performs static pattern matching for reporting purposes.
Audit Metadata