svg-article-illustrator
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local utility scripts, including 'scripts/archive.sh' for file organization and 'scripts/svg2png.js' for image conversion using Node.js.
- [EXTERNAL_DOWNLOADS]: For its PNG export functionality, the skill relies on 'puppeteer', a well-known and trusted Node.js library for headless browser automation.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes external Markdown files provided by the user.
- Ingestion points: The skill reads article content directly from user-provided file paths (e.g., '@path/to/article.md').
- Boundary markers: There are no explicit delimiters or 'ignore' instructions used when the agent reads the article content, increasing the risk of the agent following instructions embedded within the text.
- Capability inventory: The agent can execute shell scripts, run Node.js processes, read/write to the file system, and control a headless browser.
- Sanitization: The input text is not sanitized or filtered before being used to plan illustrations or generate SVG code.
Audit Metadata