excalidraw-diagram

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to save generated diagram data to a local file with the .excalidraw extension. This is the primary function of the skill and is considered safe.\n- [PROMPT_INJECTION]: The skill processes user-provided concepts to generate diagram layouts, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: User descriptions of concepts or systems (SKILL.md).\n
  • Boundary markers: Absent; there are no specific delimiters used to isolate user input from the generation logic.\n
  • Capability inventory: File system write access to create .excalidraw files (SKILL.md).\n
  • Sanitization: Absent; the skill does not specify sanitization steps for user-provided text elements or filenames.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:01 PM
Security Audit — agent-trust-hub — excalidraw-diagram