customer-journey-mapping-workshop
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of customer research and support tickets, which represents a potential surface for indirect prompt injection.
- Ingestion points: Step 0: Gather Context (SKILL.md) prompts users to paste customer research, discovery notes, and support tickets.
- Boundary markers: The skill does not provide instructions to the model to ignore embedded commands or use specific delimiters for the ingested context.
- Capability inventory: The skill is limited to interactive text generation and workshop facilitation; it does not demonstrate access to dangerous capabilities like network requests, file system modifications, or arbitrary code execution.
- Sanitization: No input validation or sanitization mechanisms for the ingested context were found.
Audit Metadata