umbraco-bundle
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (HIGH): The skill is vulnerable to Indirect Prompt Injection. It retrieves data from external URLs via WebFetch and uses that data to perform Write and Edit operations on local files.
- Ingestion points: WebFetch is used to access docs.umbraco.com in the first step of the workflow.
- Boundary markers: There are no instructions to delimit or ignore instructions found within the fetched documentation.
- Capability inventory: The skill uses Write and Edit tools to generate umbraco-package.json and manifests.ts files.
- Sanitization: No validation or sanitization of the fetched web content is performed before it is used to generate code.
- EXTERNAL_DOWNLOADS (LOW): The skill references and fetches content from docs.umbraco.com. While these are official resources, fetching content at runtime is a potential vector for malicious input.
Recommendations
- AI detected serious security threats
Audit Metadata