smtp-penetration-testing

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content provides detailed, actionable instructions for user enumeration, brute-force authentication, open-relay exploitation and even an explicit “phishing preparation” example, representing high-risk dual-use offensive capability likely to be abused.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs fetching and parsing live SMTP server responses from arbitrary targets (e.g., Phase 3 "Banner Grabbing", Phase 4 "SMTP Command Enumeration", Phase 5 "User Enumeration"), which are untrusted third-party inputs that directly drive follow-on actions like brute forcing or relay exploitation.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly instructs installing tools using sudo (e.g., "sudo apt-get install nmap/netcat/hydra/smtp-user-enum") which directs the agent to obtain elevated privileges and modify the host system, so it should be flagged.