memory-dreaming-safe@1.0.0
VERIFIED· install onlyPublisher claims: "Autonomous memory consolidation for OpenClaw agents — like REM sleep. Periodically gathers signal from daily logs, session transcripts, and learnings; consol..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
Update MEMORY.md with gathered signal:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Update MEMORY.md with confirmed changes onlyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.3. CONSOLIDATE: Update MEMORY.md — merge duplicates, absolute dates, delete contradictions, promote learningsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.7. **Update Active Plans table** — if MEMORY.md has an "Active Plans" section, update it with current plan statuses from the task_plan.md files you scannedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.5. **Promote learnings** — for each high-priority pending learning in .learnings/, add the key insight to the appropriate MEMORY.md section and update the learning's status to "promoted"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Autonomously modify long-term memory without user confirmationFix: Declare and request only the permissions the task needs.Update MEMORY.md with gathered signal. Rules:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.4. **Never delete source files** — Daily logs and learnings are append-only source material. Dreaming reads from them and writes to MEMORY.md + Obsidian. Source files are never modified or deleted.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.