monitor-ai-quality
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by design.
- Ingestion points: In Phase 2 and Phase 4 of SKILL.md, the tool
Amplitude:query_agent_analytics_sessionsis used to retrieve session data, which often contains untrusted text from user interactions with other AI agents. - Boundary markers: The instructions do not define specific delimiters or provide warnings for the agent to ignore instructions that might be embedded within the session data content.
- Capability inventory: The skill's capabilities are restricted to data retrieval, analysis, and report generation. It does not utilize tools for file system writing, arbitrary code execution, or external network operations beyond the Amplitude toolset.
- Sanitization: There are no instructions for sanitizing or filtering the session data before it is analyzed and presented in the health report.
Audit Metadata