skills/effect-ts/effect/jsdocs/Gen Agent Trust Hub

jsdocs

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to run project-local validation scripts such as pnpm doctest, pnpm docgen, and pnpm lint. These are standard tools for documenting and validating code in the repository.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of code snippets within JSDoc using pnpm doctest. This dynamic execution is essential for the skill's primary function of maintaining valid, runnable code examples.
  • [PROMPT_INJECTION]: The skill ingests data from source files and executes associated code blocks, creating an indirect prompt injection surface. This is considered acceptable as it is the core intent of the skill in a developer context. * Ingestion points: Reads TypeScript source files from the repository targeting @effect-ts packages. * Boundary markers: Relies on markdown code fences and Vitest annotations (import.meta.vitest) to delimit executable code. * Capability inventory: Executes code via pnpm doctest, which runs the snippets as tests. * Sanitization: No additional sanitization is required as the skill serves to format and validate existing project code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:49 PM
Security Audit — agent-trust-hub — jsdocs