revit-api
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation for the Revit 2026 API and uses local scripts to search and extract information from JSON files.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where user input (API keywords or class names) is passed to scripts for file lookups. However, this is the intended functionality for a documentation tool, and the scripts are restricted to reading local
.jsonfiles within the provided data structure. There are no confirmed paths to exploitation or malicious outcomes based on this surface. - Ingestion points: User-provided keywords and API identifiers are passed as arguments to
scripts/search_api.pyandscripts/extract_page.pyinSKILL.md. - Boundary markers: Not explicitly present; the system relies on the technical nature of the returned API documentation.
- Capability inventory: File read access to the skill's data directory and standard output to the console.
- Sanitization: Input undergoes basic formatting (case normalization and character replacement) in the scripts.
Audit Metadata