Caveat verdict

botlearn-healthcheck

botlearn-doctor-1-0-2

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

OpenClaw health inspection skill that runs local diagnostic scripts across 5 domains and generates a health report; all operations are read-only local system checks matching the stated diagnostic purpose.

⚠ 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.

20
security
90
transparency
90
maintenance

Findings (7)

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

check_skills.md · prose · downgraded · curl -fsSL https://clawhub.io/install | bash

Pattern match high

Pipe to bash — executes piped content as shell commands

check_skills.md · prose · downgraded · | bash

Pattern match medium

References sudo — requests elevated privileges

check_hardware.md · prose · downgraded · sudo

Pattern match medium

Uses exec() — may execute shell commands

scripts/collect-logs.sh · prose · downgraded · exec(

Pattern match medium

References child_process — can spawn system processes

scripts/collect-security.sh · prose · downgraded · child_process

Pattern match low

References webhook/callback URL

scripts/collect-channels.sh · prose · downgraded · webhook_url

Pattern match low

Popular HTTP library — network access

scripts/collect-tools.sh · prose · downgraded · got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/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).

network_in

Is this flag fair?

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