skills/howells/fiction/cover/Gen Agent Trust Hub

cover

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides usage examples for a command-line interface tool called 'motif' to generate image files from prompts. This is documented functionality for the user to execute manually.
  • [PROMPT_INJECTION]: The skill reads external project materials (README, theme files, character descriptions) to synthesize cover art concepts. This creates a surface for indirect prompt injection where malicious instructions inside project files could attempt to influence the agent's prompt generation behavior.
  • Ingestion points: README, themes, characters, world, and tone files.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Generates text-based image generation prompts.
  • Sanitization: No explicit validation or filtering of the ingested project content is performed before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 05:14 AM
Security Audit — agent-trust-hub — cover