umbraco-sections
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- Indirect Prompt Injection (LOW): The skill instructs the agent to fetch and follow instructions from external documentation URLs, which represents a potential attack surface if those external sources are compromised.
- Ingestion points: External documentation links located under the 'Documentation' header (docs.umbraco.com).
- Boundary markers: Absent; there are no specific instructions to treat the fetched documentation as untrusted data or to use delimiters.
- Capability inventory: The skill allows the 'Write' and 'Edit' tools, which would allow an agent to modify local project files based on the fetched (potentially malicious) content.
- Sanitization: None; the skill does not specify any validation or sanitization steps for the fetched content before it is used to generate code.
Audit Metadata