skills/full-stack-skills/pencil-skills/pencil-mcp-replace-all-matching-properties/Gen Agent Trust Hub
pencil-mcp-replace-all-matching-properties
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill focuses on design-related tasks within the Pencil environment and includes explicit guardrails to ensure the agent verifies user intent before execution.
- [PROMPT_INJECTION]: Evaluated for indirect prompt injection surface. Ingestion points: replacement rules in the 'properties' array (SKILL.md); Boundary markers: Absent; Capability inventory: replace_all_matching_properties tool; Sanitization: None. The risk is assessed as negligible because the tool's capabilities are restricted to modifying design properties (colors, fonts) within a design tool, with no access to sensitive system resources or network exfiltration paths.
Audit Metadata