pencil-mcp-get-style-guide
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is well-documented and restricted to retrieving style metadata (colors, fonts, etc.) based on specific IDs or tags. It does not perform any high-risk operations.
- [PROMPT_INJECTION]: No malicious injection patterns or safety bypasses were detected. On the contrary, the skill includes 'CRITICAL' instructions to ensure the agent only proceeds when the user's intent specifically involves the 'Pencil' tool.
- [EXTERNAL_DOWNLOADS]: The skill does not reference or download any external scripts, binaries, or untrusted configuration files.
- [DATA_EXFILTRATION]: There are no indicators of credential theft, sensitive file access, or unauthorized network transmissions. The tool operations are confined to the defined MCP interface.
- [COMMAND_EXECUTION]: The skill does not utilize any shell commands, system calls, or dynamic code execution patterns.
Audit Metadata