umbraco-conditions
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill exhibits a high-risk pattern by combining external data ingestion with file modification tools (Write and Edit).
- Ingestion points: SKILL.md (Workflow Step 1) explicitly directs the agent to fetch content from docs.umbraco.com using the WebFetch tool.
- Boundary markers: There are no delimiters or isolation instructions provided to prevent the agent from obeying commands embedded in the external content.
- Capability inventory: The skill is granted access to Write and Edit tools, which allow it to modify the local environment based on instructions retrieved from the external source.
- Sanitization: No sanitization or validation of the external content is implemented before it is processed for code generation.
Recommendations
- AI detected serious security threats
Audit Metadata