ClawAudit verdict

token-panel-ultimate

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Local token usage dashboard reading from local transcripts and official APIs into SQLite; skill notes explicitly state no external data sharing or cloud dependencies.

⚠ 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.

security

100

transparency

100

maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (7)

Pattern match critical

Possible hardcoded credential

BUDGET_README.md · code · API_KEY="sk-admin-...

Pattern match high

References sudo — requests elevated privileges

BUDGET_README.md · code · sudo

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/budget-panel-widget.user.js · prose · downgraded · http://127.0.0.1

Pattern match medium

Accesses OpenClaw config/secrets directly

scripts/manus-usage-fetch.py · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

Python os.getenv — reads environment variable

parsers/anthropic.py · prose · downgraded · os.getenv(

Pattern match low

Python urllib.request — network access

scripts/chatgpt-usage-fetch.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/chatgpt-usage-fetch.py · prose · downgraded · os.environ.get(

Permissions & capabilities

No declared permissions — minimal attack surface.

package_install

Is this flag fair?

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