compare-user-journeys
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure practices for data analysis, including instructions to filter internal company data and manage API rate limits through batching and retry logic.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data sources such as session replays and AI-generated feedback. While this represents a theoretical ingestion surface for indirect prompt injection, the skill uses this data exclusively for qualitative reporting and does not interpolate it into executable commands or shell environments, maintaining a safe posture.
- [COMMAND_EXECUTION]: The skill mentions reading from a file path if tool responses are too large. This is a standard platform mechanism for handling large data payloads and does not involve arbitrary command execution or unsafe file system manipulation.
Audit Metadata