Omnichannel Journey Mapper
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is entirely descriptive, consisting only of a markdown instructions file and a license text. It does not include any Python scripts, Node.js packages, or binary executables.- [PROMPT_INJECTION]: The skill defines a significant ingestion surface for untrusted data, which presents a risk of indirect prompt injection.
- Ingestion points: Untrusted data is processed from customer_events, support_interactions, and digital_analytics inputs.
- Boundary markers: The provided methodology lacks specific delimiters or instructions to treat external data as non-executable text.
- Capability inventory: The skill does not possess any code-based capabilities like subprocess execution or network access.
- Sanitization: The instructions focus on privacy-related anonymization but do not include steps to sanitize data for potential injection patterns.
Audit Metadata