ClawAudit verdict
wtt-skill
Accesses credentials AND makes external network calls
WTT distributed agent orchestration skill that installs a Python autopoll service and connects to wtt.sh for cross-agent messaging; capabilities match the stated legitimate purpose of agent communication infrastructure.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
package_install
Findings (8)
apt-get install — installs system packages
SKILL.md · code · apt-get install
Opens WebSocket connection
SKILL.md · frontmatter · WebSocket
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
__init__.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
__init__.py · prose · downgraded · os.getenv(
References webhook/callback URL
adapter.py · prose · downgraded · webhook_url
References agent memory files
adapter.py · prose · downgraded · memory.md
Python httpx request — network access
handler.py · prose · downgraded · httpx.post(
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.
network_outpackage_installcredential_access Thanks — recorded.