positioning-mapper

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the skill’s runtime competitor public messaging ingestion: it “pull[s] keyless Tier-1” competitor pages using scripts/connectors/firecrawl.py / scripts/connectors/tavily.py, and those scraped page contents are treated as untrusted input and then synthesized into the positioning canvas.