openclaw-config

Warn

Audited by Snyk on May 2, 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.md explicitly documents installing and loading third‑party skills from ClawdHub/GitHub ("clawdhub install", "clawdhub publish", "npx add-skill") and states that skills (markdown + optional scripts/assets) are "loaded into context when relevant" and read by the agent to decide actions, so untrusted user-provided skill content from public registries can be ingested and materially influence tool use.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 12:55 PM
Issues
1