umbraco-granular-user-permissions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill instructions specify using the
WebFetchtool to access documentation ondocs.umbraco.com. While these are legitimate sources for the skill's purpose, fetching external content introduces an inherent risk of ingesting unverified instructions.\n- INDIRECT_PROMPT_INJECTION (LOW): The skill demonstrates an attack surface for indirect prompt injection.\n - Ingestion points: Untrusted data enters the context via
WebFetchon external URLs in the specified workflow.\n - Boundary markers: The instructions do not define delimiters or specific 'ignore embedded instructions' warnings for the fetched content.\n
- Capability inventory: The skill allows
WriteandEditoperations, which could be misused if malicious instructions are present in the fetched documentation.\n - Sanitization: No sanitization or validation of the external content is described before use in code generation.
Audit Metadata