skills/openaec-foundation/blender-bonsai-ifcopenshell-sverchok-claude-skill-package/sverchok-impl-custom-nodes/Gen Agent Trust Hub
sverchok-impl-custom-nodes
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill provides templates for creating nodes that ingest untrusted data via Sverchok sockets using the
sv_get()method, establishing a surface for indirect prompt injection. - Ingestion points:
SKILL.md(Pattern 5),references/examples.md(Example 1, 2, 3, and 5), andreferences/methods.md. - Boundary markers: None are present in the provided templates to isolate data from potential instructions.
- Capability inventory: The
process()methods allow for arbitrary Python logic and data manipulation within the Blender environment. - Sanitization: No explicit validation or sanitization of input socket data is demonstrated in the implementation patterns.
Audit Metadata