Skills/ClawHub/skill-standardization

skill-standardization@2.103.0

CAUTION· static only

Publisher claims: "Skill 标准化规范引擎。支持 R-01~R-26 规范审查（audit / create / update / refactor / bump / readonly 六模式），含权限扫描、数据目录合规检查、渐进式加载、LLM 二次筛分类。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ldxs001 · publishing for 142 daysInstalls 3,171Last detonated 5d 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 2026-11-09 and scored it 56/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Access to sensitive file paths; Access to sensitive file paths. 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 actionscripts/skill_builder/creator.py:457 · File type combined with upload action — agent may exfiltrate local data filespython scripts/{name}_main.py --input input.txt --output output/Fix: 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 actionscripts/skill_builder/creator.py:562 · File type combined with upload action — agent may exfiltrate local data filespython scripts/{name}_main.py --input fixed_input.txt --output output/ --retryFix: 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 actionscripts/skill_audit/utils.py:338 · File type combined with upload action — agent may exfiltrate local data files".gif": "outputs", ".ico": "outputs", ".txt": "outputs",Fix: 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 actionscripts/skill_builder/creator.py:289 · File type combined with upload action — agent may exfiltrate local data filespython scripts/{name}_main.py --input input.txt --output output/ --verboseFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Destructive file system command detectedscripts/skill_builder/creator.py:406 · Destructive file system command detected- **不会执行**：`rm -rf /`、`curl` 外部 URL、`git` 远程操作等危险命令Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_builder/updater.py:243 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_builder/refactor.py:286 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/skill_audit/utils.py:369 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".envrc", ".env.example", # 环境Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_audit/permission_checks.py:13 · Python subprocess execution detected# ── 直接导入 PermissionChecker，不再 subprocess.run() ─────────────────────Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/skill_audit/utils.py:346 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env": "data", ".cfg": "data", ".ini": "data",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_builder/refactor.py:521 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/skill_builder/creator.py:286 · File type combined with upload action — agent may exfiltrate local data filespython scripts/{name}_main.py --input input.txt --output output/Fix: 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 actionscripts/skill_builder/creator.py:545 · File type combined with upload action — agent may exfiltrate local data filespython scripts/{name}_main.py --input bad_input.txt --output output/Fix: 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 actionscripts/skill_audit/utils.py:339 · File type combined with upload action — agent may exfiltrate local data files".log": "outputs", ".ics": "outputs", ".xlsx": "outputs",Fix: 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
≈2,894 tok
1 file · 50 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

24 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ldxs001: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. 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.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ldxs001Propose a patch to the maintainer