Caveat verdict

xhs

openclaw-xhs

🟢 Trusted

No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Xiaohongshu automation tool running local scripts via exec tool; all operations are documented and user-initiated.

⚠ 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.

security

transparency

maintenance

Findings (15)

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

install.sh · prose · downgraded · curl -LsSf https://astral.sh/uv/install.sh | sh

Pattern match high

Pipe to sh — executes piped content as shell commands

install.sh · prose · downgraded · | sh

Pattern match high

Possible hardcoded credential

install.sh · prose · downgraded · TOKEN="<SET_YOUR_GATEWAY_TOKEN>

Pattern match high

References sudo — requests elevated privileges

xhs-toolkit/README.md · code · sudo

Pattern match high

apt-get install — installs system packages

xhs-toolkit/README.md · code · apt-get install

Pattern match medium

Accesses OpenClaw config/secrets directly

config.example.json · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

subprocess execution — runs system commands from Python

scripts/xhs_auto_pipeline.py · prose · downgraded · subprocess.run(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/xhs_generate_content.py · prose · downgraded · http://127.0.0.1

Pattern match medium

subprocess with shell=True — command injection vector

xhs-toolkit/install_deps.py · prose · downgraded · subprocess.run(cmd, shell=True

Pattern match medium

os.system/popen — direct OS command execution

xhs-toolkit/xhs_toolkit_interactive.py · prose · downgraded · os.system(

Pattern match low

Python os.environ.get — reads environment variable

scripts/xhs_auth.py · prose · downgraded · os.environ.get(

Pattern match low

Changes file ownership

xhs-toolkit/README.md · prose · downgraded · chown

Pattern match low

Python os.getenv — reads environment variable

xhs-toolkit/src/core/config.py · prose · downgraded · os.getenv(

Pattern match low

Python shutil file operation — copies/moves/deletes files

xhs-toolkit/src/tools/manual_tools.py · prose · downgraded · shutil.copytree(

Pattern match low

Python aiohttp session — async network access

xhs-toolkit/src/utils/image_processor.py · prose · downgraded · aiohttp.ClientSession

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D/E). 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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API