analyze-feedback

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses established Amplitude tools to fetch and process data within its intended product management scope.- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing external data from feedback channels.
  • Ingestion points: Customer feedback text retrieved through the Amplitude:get_feedback_mentions tool.
  • Boundary markers: None present; the instructions do not specify delimiters for external content or warn the agent to ignore embedded instructions.
  • Capability inventory: The skill's environment is restricted to data retrieval and analysis tools; it has no access to subprocess execution, file system modifications, or arbitrary network requests.
  • Sanitization: The skill does not implement content filtering or sanitization on the raw feedback data before presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — analyze-feedback