pencil-mcp-snapshot-layout
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and associated configuration files were analyzed across all threat categories, and no malicious patterns were identified.
- [PROMPT_INJECTION]: The skill includes defensive instructions for intent recognition that require the agent to verify that the user specifically wants to use the Pencil tool before proceeding. These are safety guardrails rather than malicious injections.
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured layout data from the snapshot tool. While this creates a data ingestion surface, the risk is negligible as the tool provides a DOM-like tree structure rather than untrusted natural language instructions.
Audit Metadata