analyze-ai-topics
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted conversation data from users.
- Ingestion points: The skill uses
Amplitude:search_agent_analytics_conversationsandAmplitude:query_agent_analytics_sessions(Step 4) to fetch raw conversation samples, keywords, and enrichment data. - Boundary markers: There are no specific instructions for the agent to use delimiters (like XML tags or markdown blocks) to isolate untrusted conversation content from its own analytical instructions.
- Capability inventory: The agent has the ability to invoke various Amplitude API tools to query metrics, search sessions, and retrieve spans.
- Sanitization: The skill lacks explicit instructions for the agent to sanitize or ignore potential instructions embedded within the conversation logs it analyzes.
Audit Metadata