jsdocs
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow in
SKILL.mdinstructs the agent to execute shell commands, specificallypnpm jsdocs --checkand applicable root validation commands, to verify documentation integrity. - [INDIRECT_PROMPT_INJECTION]: The skill operates on source code and documentation which may contain untrusted data, presenting a potential attack surface.
- Ingestion points: According to
SKILL.md, the agent must inspect declarations, implementations, existing JSDoc, tests, and call sites from the project files. - Boundary markers: The instructions do not provide explicit boundary markers or warnings to disregard instructions that might be embedded within the source code or comments being processed.
- Capability inventory: The skill allows the agent to modify files ('focused API fix or module refinement') and execute shell commands (
pnpm). - Sanitization: No sanitization, validation, or filtering of the content extracted from the source files is specified in the instructions.
Audit Metadata