analyze-feedback
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted customer feedback, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: External data enters the agent's context through the
Amplitude:get_feedback_mentionstool as described inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or specific instructions to the model to disregard potential commands embedded within the user feedback quotes.
- Capability inventory: The skill's operations are limited to data retrieval and analysis within the Amplitude ecosystem; it does not contain high-risk capabilities like arbitrary shell execution, local file system writes, or external network exfiltration.
- Sanitization: No content filtering or sanitization steps are defined for the feedback mentions before they are structured into the final report.
Audit Metadata