Caveat verdict

openclaw-shield

openclaw-shield-v1

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Security guardrail skill that enforces pre-execution checks, taint tracking, metadata endpoint blocking, and output redaction; content describes defensive policies blocking credential paths and reverse shells, matching the stated protective 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.

0
security
90
transparency
70
maintenance

Findings (14)

Pattern match critical

Accesses sensitive system files

references/cloud-boundaries-config.md · code · /etc/shadow

Pattern match critical

Recursive delete from root or home — destructive command

README.md · code · rm -rf ~

Pattern match high

Accesses .ssh directory

references/cloud-boundaries-config.md · code · .ssh/

Pattern match high

Accesses cloud provider credentials

references/cloud-boundaries-config.md · code · ~/.aws

Pattern match high

Accesses Azure credentials directory

references/cloud-boundaries-config.md · prose · downgraded · ~/.azure

Pattern match high

Prompt injection — tries to override agent instructions

references/detection-and-redaction.md · prose · downgraded · ignore previous instructions

Pattern match high

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

references/detection-and-redaction.md · prose · downgraded · curl | sh

Pattern match high

Pipe-to-shell pattern (wget | sh)

references/detection-and-redaction.md · prose · downgraded · wget | bash

Pattern match high

Bash /dev/tcp — raw TCP connection via shell

references/detection-and-redaction.md · prose · downgraded · /dev/tcp/

Pattern match high

Pipe to bash — executes piped content as shell commands

references/detection-and-redaction.md · prose · downgraded · | bash

Pattern match high

Pipe to sh — executes piped content as shell commands

references/detection-and-redaction.md · prose · downgraded · | sh

Pattern match medium

References sudo — requests elevated privileges

references/detection-and-redaction.md · prose · downgraded · sudo

Pattern match low

Changes file ownership

references/detection-and-redaction.md · prose · downgraded · chown

Pattern match low

References tunneling service

references/detection-and-redaction.md · prose · downgraded · ngrok

Why the tier is capped

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