didi-board

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches typography resources from Google Fonts (fonts.googleapis.com), which is a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill requests the agent to save generated HTML files to the local ~/Downloads/ directory, which is standard behavior for a document generation tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text scripts to generate HTML presentations, creating a potential surface for indirect injection if the input contains malicious markup.
  • Ingestion points: Untrusted script text is ingested as described in SKILL.md.
  • Boundary markers: None present to delimit user content from instructions.
  • Capability inventory: The agent performs file system writes to save the resulting HTML as described in SKILL.md.
  • Sanitization: No explicit sanitization or HTML escaping is defined in the instructions for the user-supplied content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 01:44 PM
Security Audit — agent-trust-hub — didi-board