umbraco-entity-actions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill defines a workflow that ingests untrusted data from external URLs, creating a surface for indirect prompt injection.
- Ingestion points: The
WebFetchtool is used in workflow step 1 to retrieve content from external documentation URLs. - Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within fetched content.
- Capability inventory: The skill uses
WriteandEdittools, which could be manipulated by malicious instructions in the documentation to perform unauthorized file operations. - Sanitization: Absent; no validation or escaping of external content is specified.
- External Data Access (LOW): The skill performs network requests to
docs.umbraco.comvia theWebFetchtool, which is not among the pre-approved trusted domains.
Audit Metadata