docusaurus
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of documentation sites from user-provided input, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: User-provided prompts describing documentation requirements and content (SKILL.md).
- Boundary markers: Absent; there are no specific instructions for the agent to use delimiters or warnings to isolate user data.
- Capability inventory: The skill utilizes file system writes to generate project structure and shell execution for building and deploying the site (SKILL.md).
- Sanitization: The instructions do not specify a requirement for validating or escaping external content before interpolation.
- [CREDENTIALS_UNSAFE]: The skill follows security best practices regarding secret management.
- Evidence: Explicitly instructs the user to use environment variables (
process.env.SDK_API_KEY,process.env.ALGOLIA_SEARCH_API_KEY) and provides a warning: 'Never commit your API key to version control.' (SKILL.md).
Audit Metadata