skills/umbraco/umbraco-cms-backoffice-skills/umbraco-monaco-markdown-editor-action/Gen Agent Trust Hub
umbraco-monaco-markdown-editor-action
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill workflow involves ingesting external documentation to guide code generation, which introduces a surface for indirect prompt injection.
- Ingestion points: The skill's workflow uses
WebFetchto read technical documentation fromdocs.umbraco.com(file: SKILL.md). - Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore instructions embedded within the fetched documentation.
- Capability inventory: The skill possesses the
WriteandEdittools, allowing it to generate and modify files likemanifests.tsandmy-markdown-action.tsbased on the external data. - Sanitization: There is no explicit requirement for the agent to sanitize or validate the content fetched from the documentation URLs.
Audit Metadata