project-workflow
Warn
Audited by Snyk on Feb 17, 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 /explore-idea command (Phase 2: Research & Validation) and its Explore subagent explicitly use WebSearch and fetch GitHub examples, official docs, and other public websites ("Find GitHub examples and working templates", "WebSearch: ...", "Fetch official documentation"), so the agent will ingest and interpret arbitrary third‑party web/user‑generated content as part of its workflow.
Audit Metadata