openclaw-rl-training

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: 0.90). The skill explicitly captures and ingests live multi‑turn user conversations via the OpenClaw API (e.g., --enable-rl-intercept, rl_buffer / DATA_PATH, Rollout Collection) and feeds them into PRM/judge evaluation and policy training, so untrusted user-generated content can directly influence model behavior and tool use.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 05:32 PM
Issues
1