icon-set-generator

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious code or suspicious patterns were found. The skill operates entirely through natural language instructions and local file generation using predefined templates.\n- [PROMPT_INJECTION] (SAFE): The skill possesses an indirect prompt injection surface because it ingests user-provided business descriptions. However, this is considered safe as the data is used only for conceptual icon mapping and generated output is constrained to a static SVG/HTML schema.\n
  • Ingestion points: User-provided business context and industry descriptions (SKILL.md, Step 1).\n
  • Boundary markers: None explicitly defined for user input.\n
  • Capability inventory: File-write access to create the icons/ directory and its contents (SKILL.md, Step 4/5).\n
  • Sanitization: The skill utilizes strict SVG construction rules and a specific HTML template (references/preview-template.md), ensuring that user data does not influence the execution logic of the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 08:40 PM