Back to skill

Security audit

AI开发者发布助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent GitHub release-content helper, but users should be aware it relies on external services and mutable dependencies.

Install only if you are comfortable sending project metadata, prompts, generated images, and article content to the referenced search, image, and WeChat-related services. Prefer pinned or reviewed versions of the installer and delegated skills, use a public or authorized repository, and review generated content before any WeChat publication.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:70
Finding

Unpinned Third-Party Installer and Workflow Dependencies

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README is entirely presented as a Chinese-focused publishing workflow, including explicit generation of WeChat public-account articles and Chinese example content, but it does not indicate that language is configurable or optional. This can violate language/locale policy when a skill imposes a specific language without user choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The README describes automated competitor research, GitHub metadata retrieval, image generation, and article generation, but does not clearly warn users what project data, prompts, repository contents, or generated artifacts may be sent to third-party services. In a release-helper context, this can expose unpublished product details, internal roadmap information, or sensitive repository metadata to external providers without informed consent.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The README instructs users to run npx clawhub@latest install ai-dev-release-helper, which fetches and executes the latest remote package version at install time. This creates a supply-chain risk: if the package or one of its dependencies is compromised, users may execute unreviewed code with local developer privileges.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation phrases in the metadata are broad enough to match generic requests like writing announcements, product introductions, or generating cover images, which can cause the skill to trigger outside its intended GitHub-release workflow. Unintended invocation can lead to unnecessary transmission of user/project content to external services and execution of publication-oriented actions the user did not explicitly request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow description does not clearly warn users that project details, repository information, prompts, and generated assets will be sent to multiple third-party services. This omission weakens informed consent and can expose proprietary or unpublished project information, especially if users assume the skill operates locally or only within the platform.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The keyword-based activation guidance is ambiguous and unconstrained, relying on common content-production phrases that overlap with many benign user requests. In this skill, accidental activation is more concerning because the workflow chains web search, image generation, and article-generation/publishing tooling, increasing the chance of unintended data sharing or content creation on the user's behalf.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest describes the skill's purpose and workflow but does not define any explicit invocation phrases, scope limits, or exclusion conditions. For a manifest file, the lack of trigger specificity can lead to overly broad or unintended activation because it is unclear when this workflow should run versus when it should not.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description is written to produce Chinese-language deliverables, and step 3 specifically targets WeChat public-account article generation in Chinese. This indicates a fixed language/locale behavior without any visible user choice or opt-in, which is a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.