orchestrating-swarms

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly spawns research/design agents that use WebFetch/WebSearch and take arbitrary URLs (e.g., "claude-code-guide" has WebFetch/WebSearch, the Design agent "figma-design-sync" compares with a Figma URL, and Pattern 4 shows research results returned by a Task being injected into a subsequent implementation prompt), meaning the agent ingests untrusted public web/user-provided content which can directly influence follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 11:53 AM