directus-content
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with content in Directus collections, creating a surface for indirect prompt injection. * Ingestion points: The agent retrieves content from collections such as pages, posts, and blocks via the items and files tools. * Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the CMS data. * Capability inventory: The skill permits the agent to perform write operations, including creating, updating, and deleting items, as well as importing files from external URLs. * Sanitization: No steps for sanitizing, escaping, or validating the content retrieved from the CMS are mentioned.
- [SAFE]: External documentation links and resources are limited to the author's official domain (directus.com) and are used for instructional purposes.
Audit Metadata