technique-ctf

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

• Third-party content exposure detected (low risk: 0.10). The required workflow reads replies from a user-specified remote CTF target (host:port from the brief) and triage of user-supplied artifacts, which requires the agent to actively connect to a chosen target, so outsider text is exposed only after an explicit fetch, which fits the low tier.