support-response-writer
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions and templates for generating customer service scripts. It does not perform any file system operations, network requests, or command executions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input describing customer support scenarios.
- Ingestion points: User input for 'Scenario type', 'Specific issue', and 'Customer emotion' (defined in SKILL.md).
- Boundary markers: Absent. The prompt does not instruct the agent to ignore instructions that might be embedded within the user's scenario description.
- Capability inventory: No capabilities for file-writing, network-access, or subprocess execution are defined or used.
- Sanitization: None. User input is interpolated directly into the context.
- Although the ingestion surface exists, the risk is negligible as the skill lacks any impactful tools or system access to exploit.
Audit Metadata