sql-injection-stacked

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to read engagement state (which may contain credentials) and to include "New credentials or tokens found" in its return summary and evidence files, requiring the LLM to output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document contains explicit, actionable exploitation steps for stacked and second-order SQL injection—including enabling xp_cmdshell, executing arbitrary OS commands, writing webshells, COPY TO PROGRAM, inserting admin users, and data exfiltration—indicating clear malicious intent and backdoor/persistent-access techniques.

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 actions that modify system state—enabling xp_cmdshell, executing OS commands, creating user accounts, writing webshells and altering DB/system configs—so it pushes the agent to compromise the machine.