ae-proof-agent

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (e.g., references/COMPETITIVE-DILIGENCE.md and the prompts like prompts/01-DISCOVERY.md) explicitly directs the agent to consult and prefer primary public sources (URLs such as forum.cursor.com, cursor.com blog pages, and github.com/omnara-ai), meaning the agent is expected to fetch and interpret untrusted, user-generated or public web content that could influence decisions and tool actions.