skills/fikriaf/agentos/baoyu-comic/Gen Agent Trust Hub

baoyu-comic

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill demonstrates security-aware design by explicitly instructing the agent to 'Strip secrets — scan source content for API keys, tokens, or credentials before writing any output file' in its Pitfalls section.
  • [EXTERNAL_DOWNLOADS]: The workflow uses curl to download generated comic images from URLs returned by the platform's image generation tool. This is a necessary functional step for persisting the creative assets to the local file system.
  • [COMMAND_EXECUTION]: Employs standard shell utilities like curl, test, and mv for managing the comic directory structure, verifying file existence, and creating time-stamped backups of existing content during re-runs.
  • [PROMPT_INJECTION]: The skill mitigates potential indirect prompt injection risks from user-provided source material by using structured prompt templates (e.g., references/base-prompt.md) and a dedicated analysis phase that identifies core themes before generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 09:02 AM