Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Every skill must have a `SKILL.md` file with YAML frontmatter:
Security audit
Skill Publish Guide
Security checks for vulnerabilities and agentic risk
Overview
This is a transparent ClawHub publishing guide with user-invoked CLI commands and no hidden code or automatic execution.
Install only if you intend to let an agent help with ClawHub skill publishing. Review destructive or broad commands such as delete and sync --all before running them, and prefer dry-run previews for bulk operations.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Every skill must have a `SKILL.md` file with YAML frontmatter:
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Every skill must have a `SKILL.md` file with YAML frontmatter:
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Every skill must have a `SKILL.md` file with YAML frontmatter:
External Script Fetching
High
- Category
- Supply Chain
- Confidence
- 90% confidence
- Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
- Content
md | `GitHub API rate limit exceeded` | Too many requests / 请求太频繁 | Wait 10 minutes / 等待 10 分钟 | | `Connection lost while action was in flight` | Network issue or too many files / 网络问题或文件过多 | Retry with fewer files / 精简文件后重试 | | Security scan flagged missing env declaration / 安全扫描标记缺少 env 声明 | Commands use env vars not declared in frontmatter / 命令使用了未在 frontmatter 中声明的环境变量 | Add `env` section to frontmatter / 在 frontmatter 中添加 `env` | | Security scan flagged curl\|bash / 安全扫描标记 curl\|bash | Install script uses `curl \| bash` / 安装脚本使用 `curl \| bash` | Add security warning, recommend Homebrew/source build / 添加安全提示，推荐 Homebrew/源码构建 | ---
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The manifest scopes the skill to publishing, updating, deleting, or managing skills on ClawHub. Documenting
sync --allintroduces a broader bulk operation over all local skills, which is materially wider than the concrete publish/update/delete workflow presented in the manifest and may affect multiple skills at once.- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The manifest describes a skill for publishing and managing skills on ClawHub. While login checks are a reasonable prerequisite, the CLI reference expands into explicit authentication operations including
login,login --token, andlogout, which go beyond the narrow publishing-management task description and introduce account-session management behavior.- Content