ClawAudit verdict
agent-peer-tailscale
This is a legitimate VPN peer-connectivity setup guide for linking two OpenClaw agents over Tailscale; it installs Tailscale via standard package managers and configures gateway binding, all consistent with its stated purpose of enabling direct agent-to-agent communication.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
package_install
Findings (7)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -fsSL https://tailscale.com/install.sh | sh
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
Possible hardcoded credential
SKILL.md · code · Token="<peer-gateway-token>
Downloads executables from external URLs
references/tailscale-setup.md · code · download from https://
Popular HTTP library — network access
SKILL.md · code · got
subprocess execution — runs system commands from Python
scripts/peer_config.py · prose · downgraded · subprocess.run(
References tunneling service
references/tailscale-setup.md · prose · downgraded · ngrok
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outpackage_install Is this flag fair?
Thanks — recorded.