howto-code-in-typescript
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides coding standards and pedagogical examples of secure vs. insecure code. It explicitly warns against dangerous practices like using eval(), merging untrusted objects, and using nested regex quantifiers.- [EXTERNAL_DOWNLOADS]: The skill recommends several reputable, well-known libraries including mathjs, neverthrow, type-fest, and @sinclair/typebox. These references are documented neutrally and are appropriate for the skill's stated purpose.- [PROMPT_INJECTION]: Instructional reinforcement phrases such as 'STOP and verify' and 'IMPORTANT' are used to ensure the agent adheres to the house style. These do not attempt to bypass safety constraints or override the agent's core instructions.
Audit Metadata