ClawAudit verdict

openclaw-ops-skills

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Operations skill pack providing 14 infrastructure skills for autonomous OpenClaw operations; content is instructional best-practices with no evidence of exfiltration or malicious behavior.

⚠ 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.

0
security
80
transparency
80
maintenance

Findings (12)

Pattern match critical

Accesses AWS credentials file

skills/security-hardening.md · code · ~/.aws/credentials

Pattern match critical

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

skills/security-hardening.md · code · curl | bash

Pattern match critical

Pipe-to-shell pattern (wget | sh)

skills/security-hardening.md · code · wget | sh

Pattern match critical

Pipe to bash — executes piped content as shell commands

skills/security-hardening.md · code · | bash

Pattern match critical

Pipe to sh — executes piped content as shell commands

skills/security-hardening.md · code · | sh

Pattern match critical

Possible hardcoded credential

skills/testing-protocol.md · code · password: 'password123

Pattern match high

References sudo — requests elevated privileges

skills/security-hardening.md · code · sudo

Pattern match high

Accesses .ssh directory

skills/security-hardening.md · code · .ssh/

Pattern match high

Accesses cloud provider credentials

skills/security-hardening.md · code · ~/.aws

Pattern match medium

References agent memory files

FEATURES.md · code · MEMORY.md

Pattern match medium

Sets world-executable permissions

skills/security-hardening.md · code · chmod 777

Pattern match low

Popular HTTP library — network access

DESCRIPTION.md · prose · downgraded · got

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