ClawAudit verdict
autoresearch
fanta-autoresearch
The skill is designed for autonomous goal-directed iteration and optimization tasks, which seems legitimate and transparent.
⚠ 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.
Permission integrity
agent_memory
Findings (4)
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
References agent memory files
SKILL.md · code · MEMORY.md
subprocess execution — runs system commands from Python
scripts/autoresearch-loop.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
scripts/autoresearch-loop.py · prose · downgraded · subprocess.run(cmd, shell=True
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.
agent_memory Is this flag fair?
Thanks — recorded.