gtm-competitive-intel

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime research steps explicitly instruct agents to fetch and analyze outsider-authored public web content (e.g., competitor pricing pages, customer reviews on G2/Capterra/TrustRadius, LinkedIn profiles, analyst/market reports), which the agents then ingest as readable text into the LLM context.