openclaw-memory-dreaming@0.1.2
VERIFIED· install onlyPublisher claims: "A Markdown + JSON memory framework with conversation archiving for AI agents. Provides persistent long-term memory with biologically-inspired decay, recall b..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 6 of 6 bundled scripts run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 86/100 (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 · 2 s · 2 scenarios · 0 deviationsStatic findings
path.join(WORKSPACE, '.env.openrouter'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.path.join(WORKSPACE, '.env.openai'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Add to `MEMORY.md` under the right section.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- `.env.openrouter` or `.env.openai` (for API keys, summariser only)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.path.join(WORKSPACE, '.env'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if (!apiKey) throw new Error('No API key found. Set OPENROUTER_API_KEY or OPENAI_API_KEY in .env.openrouter or environment.');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `OPENAI_API_KEY` in `.env.openai` or environmentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `OPENROUTER_API_KEY` in `.env.openrouter` or environmentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// .env variable assignments with valuesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **After conversations:** Update MEMORY.md with significant factsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**Add sections to MEMORY.md** — The bootstrap script picks up `## Heading`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ng information from daily notes\n4. Review memory/dream-log.md for patterns\n5. Update MEMORY.md structure if needed\n6. Log findings to dream-log.md", "timeoutSeconds": 60…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct./\.env\b/,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Add to MEMORY.md under `## Career`:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…0.2, not structural)\n5. Run memory-supersede.js for any facts that changed\n6. Append summary to memory/dream-log.md\n7. Re-run memory-bootstrap.js to pick up new MEMORY.md entries\n\nBe selective. Only integrate what's worth remembering …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Add to MEMORY.md under `## Infrastructure`: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.