binary-diff
Warn
Audited by Snyk on Jul 4, 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's runtime code posts prompts to LLM API endpoints (e.g. https://api.deepseek.com/v1/chat/completions, https://api.openai.com/v1/chat/completions, https://api.anthropic.com/v1/messages) and directly consumes the returned YAML to drive automated renames/comments in IDA, so these URLs are runtime dependencies that directly control agent actions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata