customer-journey-mapping-workshop

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a potential surface for indirect prompt injection. Evidence Chain: 1. Ingestion points: The agent asks the user to paste customer research, discovery notes, and product context in 'Step 0: Gather Context'. 2. Boundary markers: The prompt template does not provide delimiters (like XML tags) or instructions to treat the ingested data as untrusted. 3. Capability inventory: The skill uses interactive text generation and session facilitation based on user-provided data. 4. Sanitization: No sanitization or validation of the input text is defined.
  • [NO_CODE]: The analyzed file is composed entirely of markdown instructions and YAML metadata. It contains no executable scripts, binaries, or definitions for automated system tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 06:33 AM