Caveat verdict

zrise-connect-release

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The Lobster setup instructions clone an external GitHub repository (github.com/openclaw/lobster) directly into /tmp and immediately install and execute it, introducing unverified third-party code into the agent's execution environment.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (10)

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match critical

Possible hardcoded credential

docs/TELEGRAM_INTEGRATION.md · code · token = "YOUR_BOT_TOKEN

Pattern match high

Uses spawn() — can execute external programs

docs/SIMPLE_WORKFLOW_GUIDE.md · code · spawn(

Pattern match high

Accesses OpenClaw config/secrets directly

docs/SIMPLE_WORKFLOW_GUIDE.md · code · ~/.openclaw/openclaw.json

Pattern match medium

References webhook/callback URL

docs/TELEGRAM_INTEGRATION.md · code · webhook_url

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/execute_ai_task.py · prose · downgraded · http://127.0.0.1

Pattern match medium

subprocess execution — runs system commands from Python

scripts/execute_ai_task.py · prose · downgraded · subprocess.run(

Pattern match low

References agent configuration files

scripts/agent_selector.py · prose · downgraded · agent_config

Pattern match low

Python os.environ.get — reads environment variable

scripts/execute_ai_task.py · prose · downgraded · os.environ.get(

Pattern match low

References agent memory files

scripts/zrise_utils.py · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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.

package_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API