baoyu-article-illustrator

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the terminal tool to perform file management (cp, mv, test) and download images via curl or wget. These operations are limited to the skill's specific workflow.
  • [DATA_EXFILTRATION]: The skill includes a proactive safety rule to 'Strip secrets' (API keys, tokens, credentials) from source content before any data is written to the disk or used in prompts.
  • [EXTERNAL_DOWNLOADS]: Image assets are downloaded using curl from URLs provided by the image_generate tool.
  • [SAFE]: The skill follows a structured workflow with reproducibility as a core principle, requiring prompt files to be saved before generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:31 AM
Security Audit — agent-trust-hub — baoyu-article-illustrator