skills/impertio-studio/speckle-claude-skill-package/speckle-impl-rhino-grasshopper/Gen Agent Trust Hub
speckle-impl-rhino-grasshopper
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a legitimate technical guide for a specific software integration (Speckle for Rhino/Grasshopper). The instructions are domain-specific and do not exhibit malicious behavior or security bypass attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill describes an architecture for ingesting data from external Speckle servers into a local design environment. This represents a standard functional surface for data-driven CAD workflows.
- Ingestion points: Data enters the agent's context through the
Loadcomponent which fetches models from aSpeckle Model URL(documented in SKILL.md and methods.md). - Boundary markers: The documentation does not provide specific instructions for the agent to use delimiters or sanitization logic when processing external Speckle data.
- Capability inventory: The skill enables the agent to query objects, filter by properties, mutate geometry via passthrough components, and re-publish data back to the server (methods.md).
- Sanitization: No data validation or sanitization routines are mentioned for handling ingested object properties or metadata.
Audit Metadata