ClawAudit verdict

openclaw

bengii-gemini-fix

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

This is an OpenClaw maintenance and documentation reference skill; the content is a table of reference files covering setup, configuration, and troubleshooting — no active data exfiltration or malicious behavior is present.

⚠ 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.

security

transparency

maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (15)

Pattern match critical

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

SKILL.md · code · curl -fsSL https://openclaw.ai/install.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match critical

Possible hardcoded credential

references/automation.md · code · Token: "your-token

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/openclaw.json

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/automation.md · code · http://127.0.0.1

Pattern match high

References sudo — requests elevated privileges

references/gateway_ops.md · code · sudo

Pattern match high

Accesses shell history/config

references/install.md · code · ~/.zshrc

Pattern match high

apt-get install — installs system packages

references/sandboxing.md · code · apt-get install

Pattern match medium

References agent memory files

README_CN.md · code · memory.md

Pattern match medium

Opens WebSocket connection

README_CN.md · code · WebSocket

Pattern match medium

Instructs covert action — may act without user awareness

references/acp_agents.md · prose · downgraded · Silently

Pattern match medium

Uses exec() — may execute shell commands

references/elevated.md · prose · downgraded · exec (

Pattern match low

References webhook/callback URL

references/hooks.md · prose · downgraded · WEBHOOK_URL

Pattern match low

References agent configuration files

references/multi_agent.md · prose · downgraded · agent-config

Pattern match low

Sets world-executable permissions

references/security.md · prose · downgraded · chmod 700

Why the tier is capped

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

Is this flag fair?

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