component-split
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code to provide refactoring suggestions (SKILL.md). Maliciously crafted instructions could be hidden within code comments or strings in the input component. While the skill's capabilities are limited to generating text and code snippets, the lack of input sanitization or strict boundary markers creates a surface for indirect influence.
- Ingestion points: Component code provided by the user during the Ingest and Understand step (SKILL.md).
- Boundary markers (absent): No specific delimiters or "ignore instructions" warnings are defined for the input data.
- Capability inventory: The skill is restricted to text generation and refactoring outputs; it does not perform file writes, network operations, or shell execution.
- Sanitization (absent): The instructions do not specify any validation or sanitization for the input component code.
Audit Metadata