ClawAudit verdict
content-creation-multi-agent
A multi-agent content creation toolkit with 6 specialist agents for writing, image generation, and video scripting; installation is via git clone from a named GitHub repo and openclaw gateway restart, all transparent and expected.
⚠ 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 (7)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
README.md · code · curl -fsSL https://raw.githubusercontent.com/jiebao360/content-creation-multi-ag
Pipe to bash — executes piped content as shell commands
README.md · code · | bash
Accesses shell history/config
scripts/AUTO_PUBLISH_USAGE.md · code · ~/.zshrc
References sudo — requests elevated privileges
install.sh · prose · downgraded · sudo
apt-get install — installs system packages
install.sh · prose · downgraded · apt-get install
Accesses OpenClaw config/secrets directly
scripts/configure-bot.sh · prose · downgraded · ~/.openclaw/openclaw.json
References agent configuration files
_meta_v3.json · prose · downgraded · agent_config
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
Is this flag fair?
Thanks — recorded.