Caveat verdict
clawpilot
This is an OpenClaw support/expert skill that fetches release notes and CVE advisories for staleness checks — all behavior aligns with its stated purpose as a configuration and security auditing helper.
⚠ 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.
Permission integrity
agent_memory
Findings (8)
Possible hardcoded credential
references/cloud-deployment.md · code · apiKey: "$AZURE_OPENAI_API_KEY
References agent memory files
SKILL.md · code · MEMORY.md
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
HTTP request to bare IP address — common in malicious payloads
SKILL.md · prose · downgraded · http://127.0.0.1
References webhook/callback URL
references/configuration.md · code · webhookUrl
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Opens WebSocket connection
references/security.md · prose · downgraded · WebSocket
Base64 encoding/decoding
scripts/session_scanner.sh · prose · downgraded · base64-encode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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.
agent_memory Is this flag fair?
Thanks — recorded.