netra-evaluation-setup
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided specification documents from various sources including file paths, text, and URLs.
- Ingestion points: Phase 1 reads and extracts requirements from potentially untrusted specification documents.
- Boundary markers: The instructions do not define boundary markers or 'ignore instructions' directives when processing external specification content.
- Capability inventory: The skill utilizes Grep and Read tools for codebase analysis and executes MCP tools for dataset and evaluator creation.
- Sanitization: No specific sanitization or validation logic is applied to the ingested content before it is used to generate evaluation plans and MCP payloads.
- [COMMAND_EXECUTION]: The skill suggests user execution of CLI tools for running simulations and provides code scaffolds for SDK implementation within the project environment.
Audit Metadata