umbraco-collection-action
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill utilizes the
WebFetchtool to retrieve documentation fromdocs.umbraco.com. While these are legitimate documentation sites, fetching external content is a prerequisite for indirect injection attacks. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The workflow ingests external data to automate file generation using
WriteandEdittools. - Ingestion points: Documentation URLs in
SKILL.mdaccessed viaWebFetchtool. - Boundary markers: No delimiters or instructions are provided to the agent to treat fetched content as untrusted.
- Capability inventory: The skill is granted
WriteandEditpermissions, allowing it to create or modify local files based on external input. - Sanitization: There is no mechanism to validate or sanitize the fetched documentation before it influences code generation.
Audit Metadata