fumadocs-mdx-structure
Warn
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The documentation templates generate shell commands such as
pnpm dlx shadcn@latest add @8bitcn/[component-name]. This facilitates the download and execution of code from the@8bitcnNPM scope, which is an external and unverifiable source not recognized as a trusted vendor.\n- [COMMAND_EXECUTION]: The skill instructs the agent to create documentation containing shell commands for package installation and execution.\n- [PROMPT_INJECTION]: The skill acts as a template generator that ingests metadata to produce documentation, creating an indirect prompt injection surface. \n - Ingestion points: Placeholders in SKILL.md for component names and descriptions. \n
- Boundary markers: None present to distinguish or neutralize untrusted input. \n
- Capability inventory: The skill facilitates writing MDX files to the project's documentation directories. \n
- Sanitization: No sanitization or escaping of external content is specified.
Audit Metadata