tsdoc-jsdoc-authoring
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by reading and analyzing untrusted source code provided by users, which constitutes a potential vector for indirect prompt injection.
- Ingestion points: The workflow in SKILL.md directs the agent to read target files to identify symbol purposes and side effects.
- Boundary markers: The instructions lack requirements for using delimiters to isolate untrusted code from agent instructions, and they provide no guidance to ignore instructions embedded within code comments.
- Capability inventory: The skill facilitates API analysis and documentation generation; the agent environment typically includes file read and write capabilities that could be targeted.
- Sanitization: There are no provided instructions for sanitizing, validating, or escaping the content of the source code or existing comments before processing.
Audit Metadata