ClawAudit verdict
nvidia-agent-fleet
Multi-model LLM orchestration skill using NVIDIA API; credential_access is for the NVIDIA API key used legitimately, all documented commands are standard LLM dispatch operations matching the stated purpose.
⚠ 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.
Findings (6)
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Pipe to bash — executes piped content as shell commands
dispatcher/fleet.py · prose · downgraded · |bash
subprocess execution — runs system commands from Python
dispatcher/fleet.py · prose · downgraded · subprocess.run(
Accesses OpenClaw config/secrets directly
dispatcher/fleet.py · prose · downgraded · ~/.openclaw/openclaw.json
Python os.environ.get — reads environment variable
dispatcher/fleet.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
dispatcher/fleet.py · prose · downgraded · urllib.request
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.
credential_access Is this flag fair?
Thanks — recorded.