ClawAudit verdict

agent-deploy

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The agent-deploy skill is used to deploy a new isolated OpenClaw agent with its own Telegram bot, workspace, and session storage. Although it executes a script, this action is aligned with its deployment purpose and includes safety measures like validation and auto-rollback.

⚠ 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.

68
security
90
transparency
70
maintenance

Findings (3)

Pattern match high

Possible hardcoded credential

scripts/deploy.sh · prose · downgraded · TOKEN="${2:?Usage: deploy.sh <agentId> <botToken> [workspace_path]}

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

Python os.environ.get — reads environment variable

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

Why the tier is capped

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

Is this flag fair?

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