pencil-mcp-snapshot-layout

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The analysis of the skill content and the associated MCP tool reference did not reveal any malicious patterns, obfuscation, or unauthorized data access.
  • [PROMPT_INJECTION]: The skill uses strong language like 'CRITICAL' to enforce intent verification. This is a defensive prompt design aimed at preventing the agent from misinterpreting user requests, which enhances safety rather than bypassing it.
  • [DATA_EXPOSURE]: The tool accepts an optional filePath parameter to specify which .pen file to analyze. This is a functional requirement for the design tool and does not indicate an attempt to access sensitive system files or credentials.
  • [INDIRECT_PROMPT_INJECTION]: Since the skill processes layout snapshots from external design files, there is a theoretical surface for indirect instructions. However, the skill's focus on structural hierarchy and bounds checking, combined with its restrictive intent recognition instructions, minimizes this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 05:22 PM