ClawAudit verdict
local-poi-planner
The skill uses execution sink detection, which may indicate potential risks if not properly handled.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (5)
Possible hardcoded credential
scripts/telegram_entities_demo.py · prose · downgraded · TOKEN = "YOUR_BOT_TOKEN_HERE
subprocess execution — runs system commands from Python
references/lessons-2026-06-01.md · prose · downgraded · subprocess.run(
Instructs covert action — may act without user awareness
scripts/amap_direction.py · prose · downgraded · Silently
Python os.getenv — reads environment variable
references/lessons-2026-06-01.md · prose · downgraded · os.getenv(
Python urllib.request — network access
scripts/amap_direction.py · prose · downgraded · urllib.request
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
Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.