writing-typescript
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill promotes a strong security posture by requiring that all external data from HTTP, JSON, YAML, environment variables, and storage be parsed through a schema library before entering application logic.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for untrusted data ingestion. Evidence Chain: (1) Ingestion points: 'references/type-guards.md' lists HTTP, JSON, YAML, environment, and storage as ingestion boundaries. (2) Boundary markers: The workflow mandates establishing an 'owner contract' at every I/O boundary. (3) Capability inventory: The skill involves implementing state transitions and side effects based on processed data. (4) Sanitization: The instructions explicitly demonstrate and require the use of schema parsing to validate and narrow external values before use.
- [SAFE]: No malicious instructions, obfuscation, unauthorized network operations, or persistence mechanisms were found in the skill files.
Audit Metadata