ClawAudit verdict
team-builder
Deploys a multi-agent team scaffold on the local OpenClaw instance; Telegram tokens and model API keys are noted as already-configured credentials, scripts require manual execution, and no exfiltration behavior is present.
⚠ 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 (3)
References agent memory files
SKILL.md · code · MEMORY.md
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
References agent configuration files
references/shared-templates.md · code · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/F). 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_memorynetwork_in Is this flag fair?
Thanks — recorded.