replay-ux-audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted interaction data from session replays, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The tool
Amplitude:get_session_replay_events(SKILL.md) provides interaction timelines that include user-entered inputs and form data. - Boundary markers: The instructions do not include delimiters or specific directives to ignore instructions that might be embedded within the session data.
- Capability inventory: The skill utilizes tools such as
Amplitude:get_context,Amplitude:query_chart, andAmplitude:get_feedback_insights. A successful injection could potentially bias the UX findings or lead to unauthorized data discovery within the project's Amplitude tools. - Sanitization: There is no mention of sanitizing, escaping, or filtering the content of the interaction timelines before the agent performs its synthesis.
Audit Metadata