claw-advisor
Fail
Audited by Snyk on Mar 10, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly asks to include "exact config keys... values" and to fetch live state via CLI (e.g., openclaw config/get), which can require printing sensitive config values or tokens verbatim, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md Research section explicitly instructs using "WebSearch for community solutions or GitHub issues as a fallback," so the agent will fetch and interpret untrusted public web content (community posts/GitHub issues) that can influence troubleshooting and configuration actions.
Audit Metadata