analyze-chart

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the ingestion of untrusted external data during its analysis phase.
  • Ingestion points: The skill retrieves customer feedback trends and specific mentions using Amplitude:get_feedback_insights and Amplitude:get_feedback_mentions in Step 4.
  • Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores or separates potentially malicious instructions embedded within the retrieved feedback content.
  • Capability inventory: The skill's capabilities are limited to data retrieval, segmentation, and contextual analysis within the Amplitude platform (e.g., Amplitude:query_charts, Amplitude:get_feedback_mentions). It does not appear to have access to high-risk capabilities such as arbitrary code execution or file system modifications.
  • Sanitization: Absent. The skill does not define any validation or filtering mechanisms for the data retrieved from external tools before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — analyze-chart