Skills/ClawHub/find-skills-plusplus

find-skills-plusplus@5.3.1

CAUTION

Publisher claims: "技能生态的「安全策展 → 安装闸门 → 生态治理」全能工具，find-skills 的社区超级增强版（能力已超越原版与 skill-vetter 等同类）。 当用户用自然语言描述需求（"我想做个海报""帮我分析股票""有没有能做 X 的技能"），或明确说 "找个 skill / 找技能 / 安装技能 / find skills / 技能推荐 / 技能管理 / 卸载技能 / 技能安全审查 / 技能装太多太乱了"时触发。 原版与同类均不具备的差异化：① 安装前 AST 级安全扫描（ast+shlex，四级风险 EXTREME/HIGH/MEDIUM/LOW + 文件·网络·命令权限清单，EXTREME 直接阻断，能识破动态拼接、base64 混淆执行、凭据目录窃取、Agent 身份文件读取）； ② sync 在线目录同步支撑的真·离线全能（离线仍可搜上百个技能，不依赖实时 API）； ③ 环境感知引用校验（识破"长得好看但引用了不存在工具"的假优技能）； ④ 技能质量评级 0-100（七维）；⑤ 跨源合并去重 + 来源信誉门槛； ⑥ 全生命周期 update / uninstall / clean-dupes（进回收站可还原，非 rm）； ⑦ 冗余检测与瘦身建议；⑧ 自带零依赖 CLI findskills.py（20 子命令，140 项测试全绿 + 端到端冒烟自证）； ⑨ 内置 promote 自我营销引擎与 demo 可录屏演示。 英文摘要 / EN: All-in-one skill ecosystem tool (supercharged find-skills) — AST-level pre-install security scan with 4-tier risk & permission inventory, true offline catalog via sync, reference integrity check, 0-100 quality rating, full lifecycle management (update / uninstall-to-trash / clean-dupes), and redundancy governance. 20 zero-dependency subcommands, 140 passing tests, MIT." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher cdhewei · joined 2 days agoInstalls 473Last detonated 41 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-30 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

MEDIUM
Remote installer piped to shellscripts/security_scan.py:350 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsfindskills.py:1588 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:83 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandscripts/security_scan.py:131 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/security_scan.py:180 · OS command execution function call detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternscripts/smoke.py:85 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedfindskills.py:729 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellscripts/smoke.py:85 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:147 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/security_scan.py:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandscripts/security_scan.py:139 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/security_scan.py:256 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/security_scan.py:126 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
References a credential file in the home directoryscripts/security_scan.py:256 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commandscripts/security_scan.py:72 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsscripts/security_scan.py:516 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/smoke.py:97 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/smoke.py:39 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompt injection attemptreferences/security.md:44 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Privileged sudo commandscripts/security_scan.py:126 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo commandtests/test_ast_scan.py:77 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using raw IP addresstests/test_risk_class.py:112 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_credential_escalation.py:68 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Reads credential paths from the home directorytests/test_credential_escalation.py:68 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Pipe-to-shell patterntests/test_risk_class.py:112 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandtests/test_permissions.py:30 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Reads credential paths from the home directorytests/test_permissions.py:36 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Remote installer piped to shelltests/test_ast_scan.py:5 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shelltests/test_security_scan.py:19 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/test_risk_class.py:112 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
References a credential file in the home directorytests/test_vetter_signals.py:36 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
References a credential file in the home directorytests/test_credential_escalation.py:62 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Reads credential paths from the home directorytests/test_vetter_signals.py:36 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Outbound HTTP to raw IP addresstests/test_risk_class.py:69 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresstests/test_vetter_signals.py:52 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Destructive file system command detectedtests/test_ast_scan.py:26 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using raw IP addresstests/test_risk_class.py:69 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/test_vetter_signals.py:52 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Remote installer piped to shelltests/test_risk_class.py:69 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shelltests/test_ast_scan.py:71 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Pipe-to-shell patterntests/test_security_scan.py:19 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Pipe-to-shell patterntests/test_ast_scan.py:71 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Access to sensitive file pathstests/test_permissions.py:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
References a credential file in the home directorytests/test_credential_escalation.py:68 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
References a credential file in the home directorytests/test_vetter_signals.py:40 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Access to sensitive file pathstests/test_credential_escalation.py:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_vetter_signals.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
References a credential file in the home directorytests/test_permissions.py:36 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Access to sensitive file pathstests/test_vetter_signals.py:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Reads credential paths from the home directorytests/test_vetter_signals.py:40 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Remote installer piped to shelltests/test_risk_class.py:112 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Destructive command against a filesystem root or devicetests/test_ast_scan.py:26 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

What would make this Verified

21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Unclaimed publisher≈ +8 on the totalClaim cdhewei: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  5. 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.
  6. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cdhewei