execute-mule-run-config
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill assists users in running and debugging Mule applications through a controlled interface using platform-defined tools. No malicious instructions or unauthorized access patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of project and configuration names retrieved from the workspace. 1. Ingestion points: Data enters the context via get_workspace_info and manage_run_configuration tool outputs. 2. Boundary markers: The skill requires user confirmation before execution for vague requests, which mitigates accidental execution, though it lacks explicit prompt delimiters for names. 3. Capability inventory: The skill possesses the capability to list, create, and execute configurations via manage_run_configuration. 4. Sanitization: No explicit sanitization or validation of workspace names is performed.
Audit Metadata