managing-managed-event-subscription
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill instructions and assets are limited to the generation of Salesforce metadata files.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface where user-provided strings are interpolated into XML templates without explicit sanitization. This is categorized as safe as it is the primary intended function of the skill and the generated files are metadata configurations. 1. Ingestion points: User inputs for metadata fields in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Generates XML files in the managedEventSubscriptions directory. 4. Sanitization: None identified.
Audit Metadata