Skills
Navigate
skills/specterops/skills/proxychains-tunnel/Gen Agent Trust Hub

proxychains-tunnel

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute arbitrary shell commands provided in the input parameters using the proxychains4 wrapper to tunnel traffic.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates a configuration file at /tmp/proxychains-codex.conf using a template and user-provided proxy details. This file is then used to control the behavior of the tunneling utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted command strings and proxy parameters, creating a surface for indirect prompt injection.
  • Ingestion points: COMMAND and SOCKS_HOST:SOCKS_PORT input fields in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Temporary file creation and shell command execution using the proxychains4 utility in SKILL.md.
  • Sanitization: Absent; input strings are directly interpolated into shell command templates.
  • [EXTERNAL_DOWNLOADS]: The skill performs an egress check by contacting icanhazip.com to verify connectivity and validate the external IP address of the tunnel.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:15 PM