analyze-account-health
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes account feedback which is external, potentially untrusted data that could contain hidden instructions for the agent.
- Ingestion points: Step 4 uses
Amplitude:get_feedback_insightsandAmplitude:get_feedback_mentionsto ingest textual data from users. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the feedback text.
- Capability inventory: The skill has access to
Amplitude:query_dataset,Amplitude:search, and reporting tools. - Sanitization: There is no evidence of sanitization or filtering of the retrieved feedback insights before they are processed by the agent.
Audit Metadata