ClawAudit verdict
AndonQ
tencent-andon
Accesses credentials AND writes files
Queries Tencent Cloud ticket and smart-QA APIs using AK/SK from environment variables; all endpoints are official Tencent Cloud APIs with no exfiltration.
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 writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
file_read+write
Findings (6)
Accesses shell history/config
SKILL.md · code · ~/.zshrc
subprocess execution — runs system commands from Python
check_env.py · prose · downgraded · subprocess.run(
Popular HTTP library — network access
check_env.py · prose · downgraded · got
Python os.environ.get — reads environment variable
check_env.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/andon_api.py · prose · downgraded · urllib.request
Python http.client — stdlib network access
scripts/smartqa_api.py · prose · downgraded · http.client.HTTPSConnection
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D/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.
file_writecredential_access Thanks — recorded.