Caveat verdict

zz-chat

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill deploys a Worker under the user's own Cloudflare account and registers with a central external server (ai0000.cn), creating persistent bridge infrastructure that routes user messages through an external party's coordination system.

⚠ 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.

0
security
60
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read+write

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (8)

Pattern match critical

Pipe-to-python pattern — remote code execution risk

SKILL.md · code · curl -s "$WORKER_URL/register" | python

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match critical

<script> tag in markdown — potential code injection

SKILL.md · code · <script>

Pattern match medium

Opens WebSocket connection

SKILL.md · code · WebSocket

Pattern match medium

References child_process — can spawn system processes

bridge.js · prose · downgraded · child_process

Pattern match medium

subprocess execution — runs system commands from Python

bridge.py · prose · downgraded · subprocess.run(

Pattern match low

Python urllib.request — network access

bridge.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

bridge.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class C/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.

package_installnetwork_outfile_writedata_encoding

Is this flag fair?

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