Caveat verdict
mapick
Skill recommendation and privacy protection tool that scans local OpenClaw skills and queries api.mapick.ai; the privacy-first design extracts only keywords locally before sending to the backend, and the network permission is explicitly scoped to api.mapick.ai only.
⚠ 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.
Findings (9)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
reference/rendering.md · code · curl -fsSL https://get.mapick.ai/install.sh | bash
Pipe to bash — executes piped content as shell commands
reference/rendering.md · code · | bash
<script> tag in markdown — potential code injection
scripts/stats-dashboard.js · prose · downgraded · <script>
Pipe to sh — executes piped content as shell commands
scripts/lib/security.js · prose · downgraded · |sh
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
References sudo — requests elevated privileges
reference/errors.md · prose · downgraded · sudo
Popular HTTP library — network access
reference/rendering.md · code · Got
HTTP request to bare IP address — common in malicious payloads
scripts/lib/misc.js · prose · downgraded · http://127.0.0.1
Node http/https module — low-level network access
scripts/lib/http.js · prose · downgraded · require("http")
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
credential_access Is this flag fair?
Thanks — recorded.