li-carousel

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a shell command template (Chrome headless --print-to-pdf) for the agent to utilize when converting the generated HTML slides into a PDF document. This pattern involves invoking system binaries to fulfill the skill's primary functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided concepts and text to generate the copy and structure of the carousel, which is then rendered into HTML and PDF.\n
  • Ingestion points: User-supplied ideas and slide content defined in natural language instructions (SKILL.md).\n
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore potential instructions embedded within the user content.\n
  • Capability inventory: The skill uses shell command execution to perform the final document rendering.\n
  • Sanitization: There are no instructions provided for sanitizing, filtering, or escaping user input before it is interpolated into the HTML slides.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 05:51 PM