clawd-docs-v2
Warn
Audited by Snyk on Feb 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly calls web_fetch at runtime to retrieve markdown from https://docs.clawd.bot (e.g., /tools/skills, /concepts/multi-agent, /llms.txt), and that fetched content is injected into the agent’s context to drive responses, so remote pages can directly control prompts.
Audit Metadata