skills/a5c-ai/babysitter/jsdoc-tsdoc/Gen Agent Trust Hub

jsdoc-tsdoc

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill parses untrusted source code from the project's repository to extract documentation comments, which could theoretically contain malicious instructions targeting the agent's logic.
  • Ingestion points: Source code files (.js, .ts) located within the user-provided projectPath.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within doc comments are defined in the skill instructions.
  • Capability inventory: The skill possesses Bash access for executing documentation tools and Write/Edit permissions to modify files in the project directory.
  • Sanitization: The skill does not explicitly specify sanitization or validation routines for content extracted from source comments before processing.
  • [COMMAND_EXECUTION]: The skill executes shell commands using npx to invoke tools such as typedoc. It also references the execution of local repository scripts (e.g., scripts/doc-coverage.js) for coverage analysis.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to run documentation utilities. This is standard behavior for JavaScript/TypeScript development environments to ensure the latest versions of build tools are available.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:55 AM