story-cover

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill uses user-supplied book titles and author names to build image generation prompts.
  • Ingestion points: Novel title and author name inputs in SKILL.md.
  • Boundary markers: No specific delimiters are used to separate user data from instructions in the prompt.
  • Capability inventory: Performs network requests (curl) and image manipulation (magick, sips).
  • Sanitization: Employs jq to safely escape strings for JSON payloads.
  • [EXTERNAL_DOWNLOADS]: Downloads reference images from external URLs provided by the user.
  • Evidence: Uses curl -fsSL in the image-to-image workflow.
  • [COMMAND_EXECUTION]: Runs system commands for API communication and image processing.
  • Evidence: Invokes curl, jq, base64, magick, and sips in the implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 09:38 AM