Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Auto Optimizer
v0.1.0自动监控、分析和优化OpenClaw技能性能，识别瓶颈并自动应用优化方案提升执行效率和稳定性。
⭐ 0· 37·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The stated purpose is performance monitoring and automatic optimization. The code attempts to implement that, but exports, class/method names, and behavior are inconsistent with the SKILL.md and tests. More importantly, the OptimizationApplier modifies arbitrary skill directories on disk (backing up to ~/.openclaw/backups and writing to <skillPath>/src/index.js). Modifying other skills' source code is a high-impact capability and should be clearly justified and restricted; the manifest and metadata do not surface this risk.
Instruction Scope
SKILL.md instructs callers to invoke optimizeSkill and supply a skillPath so the tool can apply changes. The code follows that model and will read/write files at the provided skillPath and create backups and metrics under the user's home directory. Additionally, the SKILL.md API surface (e.g., analyzeSkill, analyzeMultipleSkills, addRule) does not match method names implemented in the source (e.g., analyzer.analyze vs analyzer.analyzeSkill), meaning runtime behavior may not match docs. The instructions permit file modifications beyond monitoring and can be used to alter arbitrary local code.
Install Mechanism
There is no install spec (instruction-only on registry) but the package contains JavaScript source files. No network installs are declared. That lowers supply-chain install risk, but also means the skill will execute local JS code when invoked — including filesystem writes — rather than just calling an external API.
Credentials
The skill declares no required env vars, but the code reads process.env.HOME and process.env.USERPROFILE to build paths for metrics and backups. This is typical but not declared. No API keys are requested. However, the ability to write into user home paths and arbitrary provided skillPath is a powerful capability that is not reflected in the skill metadata.
Persistence & Privilege
always is false, which is appropriate. But the skill creates persistent files under ~/.openclaw (metrics and backups) and will modify other skills' source files. Autonomous invocation is allowed by default; combined with the ability to modify code on disk this increases blast radius if the skill is invoked without careful user oversight.
What to consider before installing
This package is inconsistent and risky: method names in SKILL.md, tests, and source don't line up (likely incomplete/broken), and the applier will write backups and modify other skills' source files under paths derived from HOME and a user-supplied skillPath. Before installing or enabling it: 1) review the full source locally (particularly src/applier.js) and ensure apply operations are safe and limited to intended directories; 2) run it in a sandbox or container and not on a production host; 3) require explicit confirmation and backups before allowing it to modify any code; 4) ask the author to fix the API/method-name mismatches and to add explicit safeguards (path validation, dry-run defaults, least-privileged behaviour); and 5) if you cannot audit the code, avoid granting it autonomous invocation or pointing it at repositories with sensitive credentials or production code.Like a lobster shell, security has layers — review code before you run it.
latestvk972s0g4jfgtsh0bcparge325d83yqvn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.