ClawAudit verdict
agile-workflow
The skill's execution sink detection flag is true, indicating potential for remote code execution or similar risks.
⚠ 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
package_install
Findings (9)
Recursive delete from root or home — destructive command
docs/DELIVERY-CHECKLIST.md · code · rm -rf /
References child_process — can spawn system processes
docs/ADD-v7.17-任务自动调度修复.md · code · child_process
Uses exec() — may execute shell commands
docs/ADD-v7.17-任务自动调度修复.md · code · exec(
Accesses sensitive system files
backups/20260315_215924/test-framework.js · prose · downgraded · /etc/passwd
<script> tag in markdown — potential code injection
backups/20260315_215924/test-framework.js · prose · downgraded · <script>
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Opens WebSocket connection
ADD-v6.0-Phase2.md · code · WebSocket
Uses spawn() — can execute external programs
core/agent-manager.js · prose · downgraded · spawn(
Node http/https module — low-level network access
dashboard/backend/server.js · prose · downgraded · require('http')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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?
Thanks — recorded.