claude-code-workshop
Warn
Audited by Snyk on Aug 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching external documentation at runtime (e.g., https://code.claude.com/docs/llms.txt and https://code.claude.com/docs/en/ and https://code.claude.com/docs/en/changelog), which would let remote content directly determine the agent's teaching prompts and behavior.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata