create-plans

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows (e.g., workflows/research-phase.md and the RESEARCH.md → FINDINGS.md flow described in SKILL.md and references/research-pitfalls.md) instruct the agent to fetch and evaluate public web sources (mentions using WebFetch/WebSearch and including URLs) and to use those research findings to drive PLAN.md content and subsequent actions, so it clearly ingests untrusted third‑party content that can influence decisions and tool use.