skool-monitor

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted user-generated data from Skool posts and comments via several scraping scripts. This data could contain malicious instructions designed to manipulate the agent's behavior.
  • Ingestion points: Untrusted content is fetched from Skool communities via skool_scraper.py, skool_comment_scraper.py, and skool_unreads.py.
  • Boundary markers: The skill does not implement explicit delimiters or boundary markers to isolate scraped content from the agent's instructional context.
  • Capability inventory: The skill has the ability to perform write operations (create posts, reply to comments, like content) through skool_browser_client.py and skool_client.py.
  • Sanitization: External content is parsed as JSON or HTML but lacks sanitization or filtering to detect or neutralize embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 12:41 AM
Security Audit — agent-trust-hub — skool-monitor