Caveat verdict
evermind-ai-everos
This skill installs and configures the EverOS OpenClaw plugin for persistent memory using a self-hosted backend; the setup involves local config file edits and an OpenClaw restart with no unexpected network destinations or credential exfiltration.
⚠ 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.
Permission integrity
network_out
package_install
Findings (6)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -LsSf https://astral.sh/uv/install.sh | sh
Pipe to sh — executes piped content as shell commands
SKILL.md · code · | sh
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
References child_process — can spawn system processes
bin/install.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
bin/install.js · prose · downgraded · exec(
Dynamic import() — loads module at runtime
src/subagent-assembler.js · prose · downgraded · import("
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
No declared permissions — minimal attack surface.
network_outpackage_install Is this flag fair?
Thanks — recorded.