Skills/ClawHub/agent-efficiency-manager

agent-efficiency-manager@1.0.0

CAUTION· static only

Publisher claims: "定期分析所有 Agent 的 token 使用效率，智能推荐技能配置，生成优化报告并自动推送，实现 Agent 长期自我优化。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher perrykono-debug · publishing for 169 daysInstalls 632Last detonated 21 h ago
What would fix thisWatchDispute verdict

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 2026-11-13 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This 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

MEDIUM
File type combined with upload actionSKILL.md:75 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/track_metrics.py --config ~/.qclaw/openclaw.json --history metrics_history.json --output trend_report.mdFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:41 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/analyze_agent_efficiency.py --config ~/.qclaw/openclaw.json --output metrics.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:58 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/generate_recommendations.py --config ~/.qclaw/openclaw.json --available available_skills.json --output recommendations.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈892 tok
1 file · 11 in bundle

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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim perrykono-debug: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim perrykono-debugPropose a patch to the maintainer