analyze-feedback

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted customer feedback data retrieved through the Amplitude:get_feedback_mentions tool. This creates a vulnerability surface where malicious instructions embedded in user feedback (e.g., app reviews or support tickets) could potentially be interpreted as instructions by the agent.
  • Ingestion points: Data returned by Amplitude:get_feedback_mentions described in Step 3 and used in the formatting instructions in Step 5.
  • Boundary markers: The instructions do not define clear delimiters (like XML tags or triple quotes) or provide specific directives to the agent to ignore instructions found within the feedback content.
  • Capability inventory: The skill uses tools for data retrieval (Amplitude:get_feedback_sources, Amplitude:get_feedback_insights, Amplitude:get_feedback_mentions) and user segmentation (Amplitude:get_cohorts). It does not appear to use tools for file system modification or arbitrary shell execution.
  • Sanitization: No sanitization or filtering logic is specified for the raw feedback content before it is processed for themes or quotes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:11 PM
Security Audit — agent-trust-hub — analyze-feedback