deep-plan

Warn

Audited by Snyk on Mar 5, 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's Trade-off Arbiter (references/agent-roles.md / Agent 6) is explicitly granted WebSearch/WebFetch and its prompt instructs it to "Search the web for known failure patterns", so the agent will fetch and interpret open/public web content that can influence plan decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:07 AM