canghe-article-illustrator

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs standard local file system operations, such as checking for configuration files using test -f and creating directories for output. These actions are strictly limited to the skill's operational scope (e.g., .canghe-skills/ and illustrations/).
  • [SAFE]: No external network dependencies, remote code execution patterns, or untrusted downloads were found. The skill relies on internal references and local prompt construction to interface with image generation tools.
  • [PROMPT_INJECTION]: The skill processes user-provided articles as untrusted data (Indirect Prompt Injection surface). However, it uses this data to extract themes and metrics for image prompts, which is the primary intended function, and does not exhibit any logic that could lead to agent bypass or data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 11:22 AM