ai-evolution-engine

Warn

Audited by Snyk on Mar 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The SKILL.md and implementation scripts (scripts/learn.mjs and scripts/evolve.mjs) explicitly describe "扫描ClawHub新skills"/automated discovery and installation of ClawHub skills—an open/public, user-contributed source the agent would ingest and install, which could allow third-party instructions to change agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 09:42 PM
Issues
1