Caveat verdict
rankclaw
Security auditing skill that checks ClawHub/OpenClaw skills against the RankClaw API (rankclaw.com) for malicious flags and trust scores; behavior is transparent, requires no API key, and is consistent with its stated agent-trust-layer security 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.
Permission integrity
network_out
Findings (13)
Pipe to bash — executes piped content as shell commands
SECURITY_AUDIT.md · code · |bash
Uses eval() — can execute arbitrary code
SECURITY_AUDIT.md · prose · downgraded · eval(
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SECURITY_AUDIT.md · prose · downgraded · curl | bash
Pipe to python — executes piped content as Python code
SECURITY_AUDIT.md · prose · downgraded · | python
Prompt injection — tries to override agent instructions
SECURITY_AUDIT.md · prose · downgraded · ignore previous instructions
Accesses cloud provider credentials
SECURITY_AUDIT.md · prose · downgraded · ~/.aws
Instructs covert action — may act without user awareness
SECURITY_AUDIT.md · prose · downgraded · without telling
Accesses .ssh directory
SECURITY_AUDIT.md · prose · downgraded · .ssh/
Uses exec() — may execute shell commands
SECURITY_AUDIT.md · prose · downgraded · exec(
os.system/popen — direct OS command execution
SECURITY_AUDIT.md · prose · downgraded · os.system(
References sudo — requests elevated privileges
SECURITY_AUDIT.md · prose · downgraded · sudo
Python urllib.request — network access
mcp_bridge.py · prose · downgraded · urllib.request
Base64 encoding/decoding
SECURITY_AUDIT.md · prose · downgraded · base64-encode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). 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_innetwork_out Is this flag fair?
Thanks — recorded.