guided-ooda-loop

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

• Third-party content exposure detected (high risk: 0.90). The skill's Observe/Research workflow (see Phase 1 / references/ooda-pattern.md and "Tool Usage" in Step 4) explicitly instructs the agent to "fetch web resources" and use external search tools (e.g., "peccy web search") and to include/cite links in observe/research.md, so the agent will ingest untrusted public web content that can influence decisions and next actions.