jsdocs
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to run
pnpm doctestandpnpm lintfrom the repository root to validate JSDoc examples and formatting. These are standard developer operations for verifying code quality and do not involve unauthorized execution. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external TypeScript source files, which creates a surface for indirect prompt injection if those files contain malicious instructions for the agent. However, the scope is restricted to JSDoc maintenance.
- Ingestion points: TypeScript source files, declarations, and existing JSDoc comments.
- Boundary markers: No explicit boundaries or delimiters are defined to separate code from instructions.
- Capability inventory: Execution of local
pnpmcommands for validation. - Sanitization: The instructions do not specify any sanitization or filtering of input code content.
Audit Metadata