live-data-forensics

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process external data from Amplitude, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data is retrieved via query_amplitude_data, get_amp_user_data, and manage_amp_events as described in SKILL.md.
  • Boundary markers: The instructions do not provide specific delimiters or ignore-instruction warnings for the data being processed.
  • Capability inventory: The agent has the capability to query event data, search for entities, and retrieve detailed user timelines.
  • Sanitization: The instructions do not include steps for sanitizing or validating the data returned from the Amplitude API before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:11 PM
Security Audit — agent-trust-hub — live-data-forensics