compare-user-journeys
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session replay interaction timelines and user feedback insights which represent untrusted external data.
- Ingestion points: Data enters the agent's context through tools like Amplitude:get_amp_session_replay_info (session interaction timelines) and Amplitude:use_amplitude_ai_feedback (user feedback insights).
- Boundary markers: The instructions do not specify explicit delimiters or instructions to ignore potential commands embedded within the data returned by these tools.
- Capability inventory: The skill's capabilities are focused on analytical synthesis and data retrieval via specific Amplitude tools; it does not possess capabilities for arbitrary command execution, local file system modification, or unauthorized network requests.
- Sanitization: While the skill includes instructions to exclude internal company data based on email domains, it does not specify sanitization or escaping for the content of interaction logs or feedback text.
Audit Metadata