investigate-ai-session
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 user conversation transcripts, creating an attack surface for indirect prompt injection.
- Ingestion points: Transcripts are retrieved using the
Amplitude:get_agent_analytics_conversationtool in Step 2 of SKILL.md. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to disregard potential instructions embedded within the conversation data.
- Capability inventory: The agent has access to Amplitude-specific analytical tools for querying sessions, spans, and schemas, which limits the potential impact of an injection.
- Sanitization: The instructions do not describe any sanitization or filtering of the transcript content before it is analyzed by the agent.
Audit Metadata