analyze-account-health

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes official Amplitude tools (e.g., Amplitude:query_dataset, Amplitude:get_feedback_insights) to fetch usage metrics and feedback insights for account analysis, following standard vendor resource patterns.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and processes untrusted user feedback data from external sources.
  • Ingestion points: Data enters the agent context through Amplitude:get_feedback_insights and Amplitude:get_feedback_mentions as instructed in SKILL.md.
  • Boundary markers: Absent. The skill does not implement delimiters or specific instructions to ensure the agent ignores potentially malicious commands embedded within user feedback quotes.
  • Capability inventory: No high-risk capabilities were detected. The skill is limited to data retrieval and report formatting, with no access to shell execution, file system modification, or non-whitelisted network operations.
  • Sanitization: No validation, escaping, or sanitization is performed on the retrieved feedback text before it is incorporated into the health report.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — analyze-account-health