self-learning

Warn

Audited by Snyk on Sep 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The self-learning skill searches the web and reads external documentation URLs or web pages provided by users or search engines, exposing the agent to untrusted external text.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 15, 2026, 02:34 PM
Issues
1
Security Audit — snyk — self-learning