pattern-learner
Warn
Audited by Snyk on Mar 25, 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 explicitly ingests raw HTML from extractions ("Input: html_content: Raw HTML that was extracted") and parses it with the fingerprinting code (BeautifulSoup -> generate_fingerprint) and then uses those parsed structures to generate/update learned skills and change matching/behavior, so untrusted third‑party HTML could materially influence tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata