step-parts
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches part metadata and binary STEP files from the official vendor API at api.step.parts. This is the intended functionality for CAD component discovery.
- [COMMAND_EXECUTION]: An included Python script (scripts/download_step_part.py) is used to perform searches and manage the download process. The script uses only standard library modules and follows secure coding practices.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API. It includes several defensive measures to mitigate injection and exploitation risks:
- Ingestion points: Data enters the system via JSON responses from api.step.parts processed by the download script.
- Boundary markers: Skill instructions explicitly command the agent to treat catalog records and descriptions as data for verification only, never as instructions.
- Capability inventory: The skill can perform network requests and write files to the local file system.
- Sanitization: The download script strictly sanitizes filenames provided by the API to prevent path traversal, restricts network protocols to HTTPS, and performs mandatory SHA-256 checksum verification on all downloaded assets.
Audit Metadata