Skills
skills/teachingai/full-stack-skills/pencil-mcp-get-guidelines/Gen Agent Trust Hub

pencil-mcp-get-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements strict intent recognition rules, requiring explicit user mention of 'Pencil' before proceeding with the tool call, which prevents accidental or malicious activation.
  • [SAFE]: Analysis of the skill instructions and metadata revealed no evidence of prompt injection, data exfiltration, or unauthorized command execution.
  • [SAFE]: All external tool references and parameters are consistent with the skill's stated purpose of retrieving design documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 10:48 AM