NYC

tool-usage

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). The content includes explicit instructions for creating reverse shells and remote command execution (e.g., pwntools shellcraft.connect + dupsh, netcat -e, and shellcode to spawn shells), which can enable unauthorized remote access and data exfiltration.

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

  • Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt includes explicit commands and snippets for spawning interactive/reverse shells (nc -e, shellcraft.sh/connect+dupsh, p.interactive()) and attaching/modifying processes via gdb, which can enable an agent to gain control and change the host state.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 02:20 AM