misc-tools

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content mostly contains benign CTF tooling, but it explicitly includes high-risk remote shell/remote command execution examples (nc -e, socat EXEC:/bin/bash) and other offensive commands that enable system compromise and data exfiltration, so it should be treated as malicious-capable in practice.

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

• Third-party content exposure detected (high risk: 0.80). The README's OSINT section and quick-one-liners (e.g., "sherlock username", "shodan search 'port:22'", GitHub/social media enumeration, and public repository/website lookups) explicitly instruct fetching and analyzing open/public, user-generated web content, so the skill expects ingestion of untrusted third-party data as part of its workflow.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill includes multiple "sudo apt install" commands and other system-level install instructions that modify the host system (requires elevated privileges), so it encourages changing machine state though it doesn't explicitly ask to create users or bypass security mechanisms.