umbraco-extension-registry
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill workflow requires fetching documentation from external Umbraco URLs, which exposes the agent to potential instructions embedded in third-party content.
- Ingestion points: SKILL.md (Workflow step 1) identifies several external documentation URLs.
- Boundary markers: Absent; there are no instructions to the agent to ignore or delimit embedded commands in the fetched docs.
- Capability inventory: The skill is granted 'Read', 'Write', 'Edit', and 'WebFetch' permissions.
- Sanitization: Absent; no sanitization or validation of the fetched documentation is performed before processing.
Audit Metadata