baoyu-comic
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied content (text, files, or URLs) to generate comic storyboards and image prompts.
- Ingestion points: Source content is ingested and saved to
source-{slug}.mdin Step 1.1 (references/workflow.md). - Boundary markers: The skill does not explicitly define delimiters to separate untrusted content from its internal instructions.
- Capability inventory: The skill uses
write_fileto save content andcurlvia the terminal to download images from URLs returned by theimage_generatetool (Step 7.2, references/workflow.md). - Sanitization: The skill includes a proactive security instruction to "Strip secrets — scan source content for API keys, tokens, or credentials before writing any output file" (SKILL.md).
Audit Metadata