mitm-find-checksum

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly states it will analyze a mitmproxy dump (log.txt) captured via mitmdump (see SKILL.md "Requires: log.txt in the current directory" and the mitmdump example), which means the agent ingests and acts on arbitrary third-party HTTP content captured from the open web—exposing it to untrusted, user-generated content that could contain indirect prompt-injection instructions.