monitor-ai-quality
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from AI session logs, including evaluator results and user feedback. While this represents a surface for indirect prompt injection where malicious instructions could be embedded in the processed data, the risk is assessed as safe. The skill lacks dangerous capabilities such as arbitrary command execution, file system writes, or outbound network requests, limiting the potential impact to the generated report's content.
- [SAFE]: The instructions and metadata are consistent with the skill's stated purpose of providing AI agent health reports. No signs of obfuscation, credential harvesting, or unauthorized privilege escalation were detected.
- [SAFE]: The skill relies on specific Amplitude tool calls (
Amplitude:get_amplitude_context,Amplitude:get_amplitude_agent_analytics_info) which are consistent with the vendor's intended functionality and do not exhibit patterns of data exfiltration to unauthorized third parties.
Audit Metadata