customer-feedback-triage
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (customer complaints and source inputs), establishing a surface for indirect prompt injection.
- Ingestion points: Step 1 and the Flow section specify starting from customer complaints and source input.
- Boundary markers: The instructions lack requirements for delimiters or warnings to separate untrusted content from the agent's instructions.
- Capability inventory: The skill guides the agent to perform actions such as fixing parsers, prompts, schemas, and output defects (Steps 5 and 9).
- Sanitization: No sanitization or validation steps are defined for the external content before it is processed by the agent.
Audit Metadata