openclaw-config
Warn
Audited by Snyk on Mar 15, 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 describes installing and loading third-party skills from ClawdHub and GitHub ("ClawdHub Ecosystem", "clawdhub install", "or publish to GitHub for npx add-skill") and states that "Skills ... get loaded into context when relevant" and can include scripts/assets, meaning untrusted, user-provided web content is fetched and ingested into the agent's runtime and can change its behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata