data-classification
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data elements, schemas, and architecture documentation. This creates a surface where instructions hidden within these data sources could attempt to influence the agent's behavior.
- Ingestion points: Processes user-provided data models, schemas, and processing architecture documentation (SKILL.md, Inputs section).
- Boundary markers: No explicit instructions are provided to the agent to ignore or delimit embedded instructions within the analyzed data targets.
- Capability inventory: The skill is strictly limited to analysis and documentation. It lacks capabilities for subprocess execution, file writing, or network operations.
- Sanitization: The skill specifically notes in the 'Input Sanitization' section that no user-provided values are used in commands or file paths, treating all inputs as read-only analysis targets.
Audit Metadata