article-illustrator

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash for various local tasks, including searching for assets with find, creating directories with mkdir, and copying files with cp. It also executes curl requests to a local service at http://localhost:8000 for image generation.
  • [PROMPT_INJECTION]: The skill ingests and analyzes user-supplied Markdown articles to determine image placement and generation prompts, which creates a surface for indirect prompt injection.
  • Ingestion points: Processes target Markdown articles and brand asset documentation (brand/brand-assets.md).
  • Boundary markers: No specific delimiters or instructions are used to prevent the agent from following instructions embedded within the processed articles.
  • Capability inventory: The skill utilizes Bash, Write, Edit, and WebFetch tools, allowing it to modify files based on its analysis.
  • Sanitization: There is no evidence of input validation or content sanitization for the processed articles.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 11:28 PM
Security Audit — agent-trust-hub — article-illustrator