Caveat verdict

persona-consent-telegram-hub

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Enforces explicit Telegram owner consent before sharing any persona data, denying by default on timeout or error; a consent-gating flow is a security-positive pattern.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

33
security
100
transparency
80
maintenance

Findings (5)

Pattern match critical

Possible hardcoded credential

docs/E2E-TEST.md · code · TOKEN="<from openclaw.json>

Pattern match medium

References child_process — can spawn system processes

dist/index.js · prose · downgraded · child_process

Pattern match medium

Accesses OpenClaw config/secrets directly

docs/E2E-TEST.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

Uses spawn() — can execute external programs

scripts/run-gateway-with-persona-client.js · prose · downgraded · spawn(

Pattern match low

Python os.environ.get — reads environment variable

scripts/persona_client.sh · prose · downgraded · os.environ.get(

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

Requires 3 system binaries. (1 elevated: curl).

Is this flag fair?

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