openclaw-relay

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/openclaw_relay.py leverages subprocess.run to execute local commands including node and pnpm. This is used to drive the OpenClaw and acpx CLI tools.\n- [REMOTE_CODE_EXECUTION]: The skill provides a transport mechanism to execute commands on remote hosts via SSH. It uses shlex.quote to sanitize arguments passed to the remote shell.\n- [DATA_EXFILTRATION]: The skill reads session tokens and environment configuration from paths like ~/.openclaw/gateway.token and ~/.config/openclaw/team-handoff.env. These are used locally or relayed via SSH to authenticate with the session gateway.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data for relaying to other agent sessions.\n
  • Ingestion points: User input or file content read via --text or --text-file flags in scripts/openclaw_relay.py.\n
  • Boundary markers: The build_publish_prompt function uses simple labels (e.g., 'Text:') but lacks strong structural delimiters to isolate user content from instructions.\n
  • Capability inventory: The skill possesses significant local and remote command execution capabilities (subprocess.run, ssh).\n
  • Sanitization: Content is passed to the target session without filtering for embedded instructions, though shell-level injection is prevented by shlex.quote.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 02:00 PM