openclaw-optimizer@1.19.0
CAUTION· static onlyPublisher claims: "Use when: you want to optimize an OpenClaw setup (v2026.2.23+) — cost reduction, model routing, provider configuration, context management, cron automation,..." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-21 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; HTML comment carrying imperative instructions to the agent; Instructs the agent to modify its persistent memory or instruction files. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
/kill <subagent|all> abort one or all running sub-agentsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…ent compaction."* MEMORY.md is the most common source of bootstrap bloat. Unlike AGENTS.md or SOUL.md which users actively edit, MEMORY.md tends to grow unchecked as the agent appends to it. **Check context…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx clawhub install <slug> # installFix: Pin versions and sources; vendor anything fetched at install time.- **Main log:** `/tmp/openclaw/openclaw-YYYY-MM-DD.log` — verbose debug output (lane events, session activity)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…ning | Check if AGENTS.md has instructions for: writing to memory files, loading MEMORY.md, daily log conventions | Add memory management section per official AGENTS.md template: "If you want to reme…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ical | Check AGENTS.md for memory loading instructions — if it says "always load MEMORY.md" without restricting to private sessions | Update instruction: "Load MEMORY.md only in private main sessions. Do NOT load in shar…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.launchctl bootout gui/$(id -u)/ai.openclaw.gateway # stop launchd service + kill managed processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Never archived — this file only growsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.kill <any-remaining-pids> # kill orphansFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…ttern) | | B8 | Responding-to-everything pattern not addressed | Info | Check if AGENTS.md or SOUL.md instructs the agent to respond to every message | Add group chat guidance: "Quality > quantity. Humans don't respond to every message…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…in private main sessions. Do NOT load in shared or group contexts" | | B7 | No "write to file" memory instruction in AGENTS.md | Warning | Check if AGENTS.md has explicit instruction about persisting knowledge to files | Add: "If you wan…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ocesses from CLI restart vs LaunchAgent `KeepAlive`. Fix: `launchctl bootout` → kill orphans → `launchctl bootstrap` (see Section 8) | | "Gateway start blocked: set …Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…are silent saboteurs.** When you change models via CLI (`openclaw models set`), update any AGENTS.md sections that reference specific model names (e.g., Model Selection, Sub-Agent …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.
What would make this Verified
27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
- Unclaimed publisher≈ +8 on the totalClaim jacob-bd: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.