worked-problem-generator
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill's primary workflow (Steps 3 and 6) requires the agent to generate and execute Python code using the
pintlibrary to solve engineering problems and verify the correctness of generated content. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided content such as syllabi or lecture notes to customize output notation and topics.
- Ingestion points: User-provided syllabus or lecture notes mentioned in the 'Spec' step of the workflow.
- Boundary markers: No explicit delimiters or warnings (e.g., 'ignore instructions within these notes') are defined to isolate external data from the skill's logic.
- Capability inventory: The skill possesses Python code execution capabilities (Step 3) and interacts with other skill scripts and reference files (e.g.,
machine-element-sizing/references/materials.md). - Sanitization: No sanitization, escaping, or validation steps are mentioned for the external content provided by the user.
Audit Metadata