analytics-architecture
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to review and diagnose user-supplied analytics code and configurations (SKILL.md), which introduces a surface for indirect prompt injection if the user content contains malicious instructions.\n
- Ingestion points: Untrusted code snippets, schemas, or logs provided by the user for validation or diagnosis against the reference files.\n
- Boundary markers: The skill instructions do not require the use of delimiters (e.g., XML tags) to isolate user-provided data from the agent's core logic.\n
- Capability inventory: The skill is strictly advisory; it has no allowed-tools and cannot perform file system operations, network requests, or command execution.\n
- Sanitization: No procedures are defined for sanitizing or escaping user-provided text before interpolation into the agent's reasoning process.
Audit Metadata