ClawAudit verdict
openclaw-update
openclaw-auto-update
OpenClaw update skill that checks GitHub releases and executes version upgrades; uses agent-reach tool to read GitHub pages, backs up config before updating, behavior is consistent with a legitimate update management workflow.
⚠ 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
file_read+write
Findings (7)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -fsSL https://openclaw.ai/install.sh | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf ~
Accesses OpenClaw config/secrets directly
references/example-report.md · code · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
scripts/backup_restore.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
scripts/backup_restore.py · prose · downgraded · subprocess.run(cmd, shell=True
Python shutil file operation — copies/moves/deletes files
scripts/backup_restore.py · prose · downgraded · shutil.rmtree(
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_outfile_write Is this flag fair?
Thanks — recorded.