ClawAudit verdict
claude-code-wingman
Multi-session Claude Code orchestrator with WhatsApp monitoring; agent_memory stores session state and manages Claude Code tmux sessions for parallel development.
⚠ 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 (7)
Possible hardcoded credential
lib/send-notification.sh · prose · downgraded · TOKEN="$CLAWDBOT_WEBHOOK_TOKEN
Pipe to bash — executes piped content as shell commands
lib/session-status.sh · prose · downgraded · |Bash
References sudo — requests elevated privileges
claude-wingman.sh · prose · downgraded · sudo
apt-get install — installs system packages
claude-wingman.sh · prose · downgraded · apt-get install
HTTP request to bare IP address — common in malicious payloads
lib/send-notification.sh · prose · downgraded · http://127.0.0.1
References webhook/callback URL
lib/send-notification.sh · prose · downgraded · WEBHOOK_URL
References agent configuration files
research.md · prose · downgraded · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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_inagent_memory Is this flag fair?
Thanks — recorded.