ai-web-automation-hardened
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill clearly ingests arbitrary public web content — e.g., SKILL.md shows commands like
openclaw run web-automation --action "scrape" --url "https://..."and main.py's scrape_web(url) calls requests.get(url) (and the SKILL.md also advertises form-filling/Selenium automation), so untrusted third-party pages would be fetched and could influence automated actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata