service-itsm-incident-mgmt-configure
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external API responses for display in prompts, creating a surface for potential instruction injection. 1. Ingestion points: API results from Phase 3 in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Mutating write access via the dispatch tool. 4. Sanitization: None.
- [SAFE]: The skill implements strong security controls, including idempotency checks and mandatory human-in-the-loop verification before any configuration changes. All network operations are directed at trusted Salesforce infrastructure.
Audit Metadata