reviewing-typescript-code
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted TypeScript source code and Pull Request diffs which creates an attack surface for instructions embedded in data.
- Ingestion points: SKILL.md defines the skill's primary use as 'reviewing PRs' and checking 'code before commit'.
- Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore natural language instructions found within code comments or string literals in the reviewed files.
- Capability inventory: The skill possesses file reading and searching capabilities through the 'Read', 'Grep', and 'Glob' tools.
- Sanitization: No sanitization or filtering logic is specified to prevent the agent from potentially following instructions found within the code it analyzes.
Audit Metadata