visual-prompt-engine

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill implements an indirect prompt injection surface (Category 8) by scraping and processing content from an external website.
  • Ingestion points: scripts/scrape_dribbble.py fetches titles and descriptions from dribbble.com.
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions for the agent to ignore commands within the scraped data.
  • Capability inventory: The data is used for generating text prompts; no high-risk capabilities like shell execution or file writing are exposed to the external content.
  • Sanitization: Minimal. The scraper uses regex to remove HTML tags but does not filter for instructional keywords.
  • External Downloads (LOW): The scripts/scrape_dribbble.py script uses urllib.request and optionally requests to fetch data from dribbble.com. As this domain is not on the predefined whitelist, the network activity is flagged as a low-level concern.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 04:30 PM