ts-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code provided by the user. While this creates an attack surface, the risk is minimized by the skill's specific objective and its built-in redaction logic.
- Ingestion points: Target source code files analyzed during Step 1.
- Boundary markers: Analysis is strictly guided by predefined library references (Total TypeScript, etc.).
- Capability inventory: Reading local code files and internal library documentation.
- Sanitization: A dedicated 'Redact secrets' phase (Step 4) specifically masks keys, tokens, and passwords before any report is generated.
- [COMMAND_EXECUTION]: The skill includes a shell command to locate its library configuration. This command is a fixed, non-interactive diagnostic check used to resolve local environment paths and does not involve external network calls or vulnerable user input.
Audit Metadata