john

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to run John to crack hashes and display plaintext passwords (e.g., john --show and wrapper scripts that emit results), which requires the agent to receive and output secret credential values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content provides explicit, actionable instructions for obtaining and cracking password hashes (e.g., unshadow /etc/shadow, zip2john/rars/pdf2john, john --incremental/--wordlist), which directly facilitates credential theft and unauthorized access — no hidden network exfiltration or remote-backdoor code is present, but the guidance is high-risk and can be used maliciously.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs the agent to read and crack /etc/shadow (via unshadow and john) and run local password-cracking operations, which require elevated access to system-protected files and directly compromise the machine's security state.