T08 · Insecure Dependencies
- Location
README.md:70- Finding
Unpinned Third-Party Installer and Workflow Dependencies
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
README.md:70Unpinned Third-Party Installer and Workflow Dependencies
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.
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 In a release-helper context, this can expose unpublished product details, internal roadmap information, or sensitive repository metadata to external providers without informed consent.
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.
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.
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.
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.
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.
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.