ClawAudit verdict

unified-mailbox-ai

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill transparently declares its credential requirements (MS_GRAPH_ACCESS_TOKEN, Gmail account, Telegram chat ID) and uses them for their stated purpose of unified email monitoring with calendar conflict detection.

⚠ 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.

55
security
80
transparency
70
maintenance

Findings (6)

Pattern match medium

Downloads executables from external URLs

install.sh · prose · downgraded · Install from https://

Pattern match medium

Accesses OpenClaw config/secrets directly

README.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

subprocess execution — runs system commands from Python

scripts/unified_mailbox_ai.py · prose · downgraded · subprocess.run(

Pattern match medium

Instructs covert action — may act without user awareness

scripts/unified_mailbox_ai.py · prose · downgraded · silently

Pattern match low

pip3 install — installs Python packages at runtime

install.sh · prose · downgraded · pip3 install

Pattern match low

Python os.environ.get — reads environment variable

scripts/unified_mailbox_ai.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 environment variable. Requires 1 system binary.

Is this flag fair?

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