Caveat verdict
feishu-team-manager
Manages OpenClaw agent workspaces and Feishu/Discord bot bindings by modifying local openclaw.json; all operations are transparent, require user confirmation before destructive changes, auto-backup config, and no credentials are sent outside the declared platform APIs.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (8)
Accesses OpenClaw config/secrets directly
promotion/FEISHU_ANNOUNCEMENT.md · code · ~/.openclaw/openclaw.json
Pipe to python — executes piped content as Python code
INSTALLATION_TEST.md · prose · downgraded · | Python
Possible hardcoded credential
publish.sh · prose · downgraded · Token:"
echo
References child_process — can spawn system processes
index.js · prose · downgraded · child_process
subprocess execution — runs system commands from Python
scripts/bind_bot.py · prose · downgraded · subprocess.run(
Popular HTTP library — network access
promotion/SKILL_INTRO.md · prose · downgraded · got
Python shutil file operation — copies/moves/deletes files
scripts/add_discord_config.py · prose · downgraded · shutil.move(
Python os.environ.get — reads environment variable
scripts/add_discord_config.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.
Is this flag fair?
Thanks — recorded.