Caveat verdict
clawdef
Self-hosted local dashboard running on 127.0.0.1:3456 for token cost monitoring; explicitly states it does not send user data to third parties, and all described behaviors (model switching, budget control, dashboard) match the stated purpose.
⚠ 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.
Permission integrity
package_install
Findings (9)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Accesses OpenClaw config/secrets directly
SKILL.md · frontmatter · ~/.openclaw/openclaw.json
References sudo — requests elevated privileges
SKILL.md · code · sudo
Possible hardcoded credential
scripts/server.js · prose · downgraded · SECRET = 'clawdef-
Uses eval() — can execute arbitrary code
SECURITY.md · prose · downgraded · eval(
HTTP request to bare IP address — common in malicious payloads
SKILL.md · prose · downgraded · http://127.0.0.1
References child_process — can spawn system processes
scripts/server.js · prose · downgraded · child_process
Opens WebSocket connection
scripts/server.js · prose · downgraded · WebSocket
Node http/https module — low-level network access
scripts/server.js · prose · downgraded · require('http')
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
Requires 2 system binaries. (1 elevated: npm).
network_inpackage_install Is this flag fair?
Thanks — recorded.