ClawAudit verdict

humanos

humanos-openclaw

🟠 Risky

Significant concerns — only install if you understand the risks

The skill accesses credentials which could potentially be used for malicious purposes, but for now it seems to be used for legitimate authorization purposes.

⚠ 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

maintenance

Findings (4)

Pattern match high

Accesses OpenClaw config/secrets directly

README.md · code · ~/.openclaw/openclaw.json

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("credential") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · 1. Confirm endpoint is `https://api.humanos.id`. 2. Confirm timestamp is 13-digit numeric milliseconds. 3. Confirm signing payload is exactly: - `timestamp + ".

Pattern match low

Accesses sensitive environment variables

hooks/humanos-guard/handler.ts · prose · downgraded · process.env.VIA_SIGNATURE_SECRET

Pattern match low

Popular HTTP library — network access

scripts/test-all.sh · prose · downgraded · got

Why the tier is capped

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

Permissions & capabilities

Requires 2 environment variables. (2 sensitive: VIA_API_KEY, VIA_SIGNATURE_SECRET). Requires 4 system binaries. (1 elevated: curl).

credential_access

Is this flag fair?

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