Security audit

GitHub Actions ClawHub Doctor

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only diagnostic skill for GitHub Actions to ClawHub publishing failures, with no hidden execution, persistence, or unrelated data handling found.

Install this if you want help diagnosing ClawHub publishing failures from GitHub Actions. Be aware that much of the documentation is in Chinese, and only share workflow logs or configuration details you are comfortable exposing; secret token values themselves should not be pasted into chats or logs.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: This markdown file contains user-facing natural language only in Chinese across the changelog entries, with no indication that the language was selected by the user or that the skill is intentionally region-specific. Under the policy, forcing a specific language without opt-in can be a locale-policy violation.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The description includes Chinese text as part of the primary skill description, which can impose a language expectation on users without explicitly offering a language or locale choice. This is a natural-language policy concern because the file does not state that the skill is region-specific or that users may choose their preferred language.

Vague Triggers

Low

Confidence: 79% confidence
Finding: The invocation examples '帮我查为什么 github actions 发不到 clawhub' and '看看这次 workflow 红灯到底卡在哪一层' are descriptive but still broad natural-language requests rather than tightly scoped activation phrases. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The entire file is written in Chinese and provides no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.