webwork-writer-expert

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Skill analysis complete.
  • [COMMAND_EXECUTION]: The skill includes a Python script (lint_pg_via_renderer_api.py) for linting WeBWorK problem files. This script is intended to be run locally to communicate with a developer-managed renderer instance on localhost:3000.
  • [EXTERNAL_DOWNLOADS]: Reference documentation includes examples that load the RDKit.js library from unpkg.com. This is a standard and well-known CDN service used for the legitimate purpose of rendering molecular structures within educational problems.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data transfer was detected. The linting script explicitly includes logic to redact and strip JSON Web Tokens (JWT) from its output to prevent accidental exposure of sensitive session data during development.
  • [PROMPT_INJECTION]: Instructions provide clear, professional guidelines for problem authoring and mandate reading reference documentation before editing files, with no attempts to bypass safety filters or override agent constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:44 PM