claude-to-deerflow

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly interacts with a DeerFlow agent platform that "orchestrates sub-agents for ... web browsing" (SKILL.md) and the runtime scripts (scripts/chat.sh) can enable subagents via "subagent_enabled": true (ultra mode), meaning the agent may fetch and return content from open/public third‑party sites which the skill parses and acts on.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 03:07 PM