infographic-creator

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill generates HTML code that fetches the AntV Infographic library from unpkg.com, which is a well-known and standard content delivery network for NPM packages.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use a file-writing tool to save generated HTML files to the local system, which is the primary intended function of the infographic creator.
  • [PROMPT_INJECTION]: The skill takes untrusted user input and embeds it into a template that is subsequently written into a JavaScript string within an HTML file. While this creates a potential surface for indirect prompt injection or cross-site scripting (XSS) if the generated file is opened in a browser, this behavior is central to the skill's purpose as a content creator.
  • Ingestion points: User-provided text content (SKILL.md).
  • Boundary markers: None identified in the HTML generation template.
  • Capability inventory: File-writing tool (SKILL.md).
  • Sanitization: None identified; the skill directly interpolates input into script backticks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 02:59 PM
Security Audit — agent-trust-hub — infographic-creator