analyze-account-health
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources that could contain malicious instructions.
- Ingestion points: The skill retrieves customer feedback, pain points, and mentions through tools like
Amplitude:get_feedback_insightsandAmplitude:get_feedback_mentionsin Step 4. - Boundary markers: There are no explicit instructions or delimiters defined to separate the retrieved feedback text from the agent's instructions, nor are there warnings to ignore any commands embedded within the feedback.
- Capability inventory: The skill possesses capabilities to search, query datasets, and retrieve feedback metadata/content using the Amplitude toolset. It does not appear to have file-write or arbitrary network execution capabilities.
- Sanitization: The instructions do not specify any sanitization, filtering, or escaping for the feedback content before it is processed and summarized by the agent.
Audit Metadata