replay-ux-audit
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from session interaction timelines and user feedback.
- Ingestion points: The skill utilizes
Amplitude:get_session_replay_eventsto retrieve interaction timelines (including inputs) andAmplitude:get_feedback_insightsfor customer feedback content in SKILL.md. - Boundary markers: The instructions do not define delimiters or specific safety markers to differentiate between external data and the agent's core instructions.
- Capability inventory: The skill has access to the Amplitude toolset (
get_session_replays,query_charts, etc.) to retrieve data and generate reports. It does not possess capabilities for arbitrary command execution or file system modification. - Sanitization: The instructions do not include steps for sanitizing, escaping, or validating the external content retrieved from the Amplitude API before it is analyzed by the agent.
Audit Metadata