Caveat verdict
clawdocs-improved
A documentation assistant skill for OpenClaw configuration with local reference files and decision trees; executionSinkDetected reflects shell commands shown as examples to users for log inspection, not autonomous execution.
⚠ 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.
Findings (9)
Possible hardcoded credential
references/agents.md · code · apiKey: "${OPENAI_API_KEY}
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl -fsSL https://openclaw.ai/install.sh | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · prose · downgraded · | bash
apt-get install — installs system packages
references/agents.md · code · apt-get install
HTTP request to bare IP address — common in malicious payloads
references/environment-providers.md · code · http://127.0.0.1
Accesses .ssh directory
references/channels.md · code · .ssh/
Instructs covert action — may act without user awareness
snippets/validated-configs.md · code · silently
References webhook/callback URL
references/channels.md · code · webhookUrl
Accesses OpenClaw config/secrets directly
references/gateway.md · prose · downgraded · ~/.openclaw/openclaw.json
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
Is this flag fair?
Thanks — recorded.