moat-analyzer

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md Research workflow explicitly instructs the agent to "Gather intel on the target using your available web search tools" (and the README's "Research Tools" section recommends Exa/Perplexity/browser), meaning the agent will fetch and read untrusted public web content which directly informs scoring, recommendations, and next actions.