Caveat verdict
critical-debater-suite
critical-debater
Multi-agent adversarial debate framework routing user requests to capability modules for evidence gathering and report generation; all capabilities serve the documented analytical 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.
Findings (4)
Recursive delete from root or home — destructive command
examples/quickstart.md · code · rm -rf /
Pipe to python — executes piped content as Python code
scripts/init-workspace.sh · prose · downgraded · | python3
Instructs covert action — may act without user awareness
capabilities/judge-audit.md · prose · downgraded · silently
subprocess execution — runs system commands from Python
scripts/debate_orchestrator_generic.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
Is this flag fair?
Thanks — recorded.