php-code-injection

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires collecting, saving, and returning discovered credentials/tokens and evidence, which forces the agent to include secret values verbatim in its output (exfiltration risk).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill provides explicit, step-by-step instructions to exploit PHP code injection for remote code execution, data exfiltration, reverse shells/webshell planting, and disable_functions bypasses — behaviors consistent with deliberate backdoor and malicious abuse.

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 achieving PHP code injection that executes OS commands, writes files (e.g., webshells to /tmp or webroot), and spawns reverse shells, all of which modify and compromise the host system.