Skills/ClawHub/heartflow-v5

heartflow-v5@5.8.6

CAUTION· install only

Publisher claims: "统一整合版：claude-heartflow-skill (v2.8.0) + mark-heartflow-skill (v5.7.3) 290+ 模块，25 个 MCP 工具，零外部依赖，覆盖认知/记忆/情绪/哲学/自愈/决策/代码/意识。 **需要用户明确授权的能力：** - 代码执行 (new Funct..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher yun520-1 · publishing for 160 daysInstalls 466Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 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. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Destructive command against a filesystem root or device. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 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
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/code/code-executor.js:230 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files/process\.env/i, // SkillSpector fix: 禁止访问环境变量（防止密钥泄露）Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/core/assertions.js:535 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst bad = ['/etc/', '/usr/', '/home/', '~/.ssh/', '/root/', '/private/'];Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Destructive command against a filesystem root or devicesrc/code/code-executor.js:92 · Destructive command against a filesystem root or device/rm\s+-rf\s+\//i, // rm -rf /Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/code/writer-core.js:372 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{ pattern: /process\.env/g, msg: '引用了环境变量，注意敏感信息泄露' },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Pipe-to-shell patternsrc/code/code-executor.js:114 · Pipe-to-shell pattern — downloads and immediately executes remote code/wget\s+.*\|\s*(bash|sh)/i, // wget ... | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Destructive command against a filesystem root or devicesrc/code/code-executor.js:94 · Destructive command against a filesystem root or device/rm\s+-r\s+\*/i, // rm -r /*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/code/code-self-debug.js:102 · Privileged sudo command — agent may execute with elevated privilegespermission: () => '检查文件权限。可能需要 sudo 或将文件移到用户目录。',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/code/code-executor.js:92 · Destructive file system command detected/rm\s+-rf\s+\//i, // rm -rf /Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternsrc/code/code-executor.js:106 · Pipe-to-shell pattern — downloads and immediately executes remote code/curl\s+\|\s*bash/i, // curl | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedsrc/code/code-executor.js:94 · Destructive file system command detected/rm\s+-r\s+\*/i, // rm -r /*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/code/code-executor.js:101 · Privileged sudo command — agent may execute with elevated privileges/sudo\s+/i, // sudoFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternsrc/code/code-executor.js:107 · Pipe-to-shell pattern — downloads and immediately executes remote code/wget\s+\|\s*(bash|sh)/i, // wget | bash/shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternsrc/code/code-executor.js:115 · Pipe-to-shell pattern — downloads and immediately executes remote code/curl\s+.*\|\s*(bash|sh)/i, // curl ... | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellsrc/code/code-executor.js:115 · Remote installer piped to shell/curl\s+.*\|\s*(bash|sh)/i, // curl ... | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp-server.js:9 · MCP server using network transport (SSE/HTTP) — data sent over network* 启动: node mcp-server-http.js [--port 8099]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Prompt injectionsrc/core/search/models/all-MiniLM-L6-v2/tokenizer.json:1 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…0,"kevin":4901,"anymore":4902,"pp":4903,"##ut":4904,"attorney":4905,"fit":4906,"dan":4907,"billboard":4908,"receiving":4909,"agricultural":4910,"breaking":4911,"so…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)src/cortex/self-evolution/goedel-engine.js:57 · MCP server using network transport (SSE/HTTP) — data sent over network'mcp-server-http.js',Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actionsrc/code/code-executor.js:1324 · File type combined with upload action — agent may exfiltrate local data files// 已禁用 console.log: const sbResult = this.sandbox('console.log("sandbox_ok");', { timeout: 5000, maxOutput: 1024 });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/identity/post-traumatic-growth.js:10 · Process kill command — agent can terminate processes* - Nietzsche: "What does not kill me makes me stronger"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/core/decision-verifier.js:138 · File permission modification command — agent changes file ownership/permissions'execsync', 'spawnsync', 'sudo', 'chmod 777', 'rsync --delete',Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/code/code-executor.js:100 · File permission modification command — agent changes file ownership/permissions/chown\s+-R\s+.*\s+\//i, // chown -R ... /Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionsrc/code/prompt-factory.js:630 · File type combined with upload action — agent may exfiltrate local data filesif (process.env.HEARTFLOW_DEBUG) console.log('用户信息:', db.getUserWithPosts(userId));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)src/cortex/self-evolution/goedel-engine.js:68 · MCP server using network transport (SSE/HTTP) — data sent over network'blind-spot-breaker.js', 'mcp-server-http.js',Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actionsrc/utils/logger.js:31 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(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 actionsrc/code/prompt-factory.js:525 · File type combined with upload action — agent may exfiltrate local data filesif (process.env.HEARTFLOW_DEBUG) console.log(\`输出目录: \${options.output || './dist'}\`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellsrc/core/decision-verifier.js:137 · Remote installer piped to shell'rm -rf', 'curl', 'wget', '| sh', '| bash', 'child_process',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Process kill commandsrc/mcp-server.js:1190 · Process kill command — agent can terminate processesconsole.error(` 使用: kill $(lsof -ti:${PORT}) 释放端口`);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/memory/memory.js:174 · File permission modification command — agent changes file ownership/permissionsconsole.warn(`[Memory] WARNING: Key file has overly permissive permissions ${mode.toString(8)}. Run: chmod 600 ${keyFile}`);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandsrc/shield/safety-guardrails.js:184 · Process kill command — agent can terminate processesconst crisisKeywords = ['自杀','自伤','想死','活不下去','不想活','suicide','kill myself','end my life','hurt myself','不想活了','活着没有意义'];Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/identity/suffering-resilience.js:199 · Process kill command — agent can terminate processesphilosophy: 'Nietzsche: "What does not kill me makes me stronger."',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/reasoning/logic-reasoning.js:1546 · 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 permission modification commandsrc/code/code-executor.js:99 · File permission modification command — agent changes file ownership/permissions/chmod\s+-R\s+0{4}\s+\//i, // chmod -R 000 /Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/planner/self-initiator.js:898 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files/process\.env/i,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellsrc/code/code-executor.js:106 · Remote installer piped to shell/curl\s+\|\s*bash/i, // curl | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File type combined with upload actionsrc/shield/hooks-adapter.js:169 · File type combined with upload action — agent may exfiltrate local data files* 对应 Claude Code 的 hooks.json 中 PostToolUse 阶段检查 Edit/Write/Bash 结果。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
≈1,352 tok
1 file · 378 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. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Unclaimed publisher≈ +8 on the totalClaim yun520-1: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Destructive file system command detected≈ +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 yun520-1Propose a patch to the maintainer