pencil-mcp-get-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill is composed entirely of markdown documentation and configuration for an MCP tool call.
  • [SAFE]: The skill implements a 'Critical Prerequisite' for intent recognition, requiring explicit user mention of the service ('Pencil') before tool invocation, which serves as a protective constraint against accidental or malicious trigger phrases.
  • [SAFE]: The input parameters for the guidelines tool are restricted to a predefined set of topics, limiting the potential for unexpected input or parameter injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 05:22 PM