analyze-account-health

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from user feedback which could contain malicious instructions.
  • Ingestion points: The skill retrieves feedback insights and specific mentions (quotes) using the Amplitude:use_amplitude_ai_feedback tool in SKILL.md (Step 4).
  • Boundary markers: The instructions do not define specific delimiters or headers to isolate external user feedback from the agent's system instructions.
  • Capability inventory: The skill utilizes Amplitude-specific tools (search_amp_entities, query_amplitude_data, use_amplitude_ai_feedback) to generate a structured report. It does not have access to general shell execution, file system writes, or arbitrary network requests.
  • Sanitization: There is no mention of sanitization, filtering, or validation of the text retrieved from the feedback tool before it is processed or presented in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:11 PM
Security Audit — agent-trust-hub — analyze-account-health