mcaf

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly directs the agent to consult and install from public web sources (e.g., "https://mcaf.managed-code.com/tutorial", "https://mcaf.managed-code.com/", and "https://skills.managed-code.com/") as canonical bootstrap and skills catalog pages, meaning the agent is expected to fetch and act on untrusted third-party content that could contain instructions influencing tool use and decisions.