baoyu-article-illustrator
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses simple shell commands (
test -f) to check for the presence of configuration files in the.baoyu-skills/directory and the user's home directory. These checks are benign and used solely for preference management. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes untrusted article content to generate image prompts and document updates.
- Ingestion points: Articles provided via file paths or pasted text as described in Step 1.1 of the workflow.
- Boundary markers: The skill does not explicitly use delimiters to isolate the article content from its internal instruction logic during analysis.
- Capability inventory: The skill can read and write files (updating articles) and invoke an image generation tool.
- Sanitization: No explicit sanitization or filtering of the input article content is mentioned in the instructions.
- [SAFE]: The skill follows secure practices for file management, such as asking for confirmation before overwriting existing images and offering to create copies of articles rather than modifying originals. No evidence of data exfiltration, credential theft, or persistence mechanisms was found.
Audit Metadata