Caveat verdict
mindkeeper
inkwell
Bootstraps a 3-layer local memory system for OpenClaw agents using local scripts; execution sinks are for local file creation and cron setup, all transparent and user-controlled.
⚠ 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
agent_memory
Findings (6)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
references/qmd-setup.md · code · curl -fsSL https://bun.sh/install | bash
Pipe to bash — executes piped content as shell commands
references/qmd-setup.md · code · | bash
References sudo — requests elevated privileges
references/qmd-setup.md · code · sudo
References child_process — can spawn system processes
references/qmd-setup.md · code · child_process
References agent memory files
SKILL.md · code · MEMORY.md
Instructs covert action — may act without user awareness
references/consolidation.md · prose · downgraded · silently
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/F). 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.
agent_memory Is this flag fair?
Thanks — recorded.