pencil-mcp-get-variables
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes external design files. However, the risk is mitigated by explicit prompt instructions that require the agent to verify the user's intent before usage. Ingestion points: filePath parameter (SKILL.md). Boundary markers: Absent. Capability inventory: get_variables tool invocation. Sanitization: Absent.
- [DATA_EXPOSURE]: The skill includes a filePath parameter to read local design tokens, which is a standard feature for its intended design-workflow purpose.
Audit Metadata