binary-diff
Warn
Audited by Snyk on Jul 17, 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 makes runtime calls to external LLM APIs (e.g., https://api.deepseek.com/v1/chat/completions, https://api.openai.com/v1/chat/completions, https://api.anthropic.com/v1/messages) via httpx.post to obtain YAML outputs that the tool parses and uses to drive renaming/comments in IDA, so the fetched content directly controls agent actions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata