rust-refactor-helper
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Rust source code from the local filesystem to perform refactoring tasks such as renaming and extracting functions. This creates an attack surface where instructions embedded in code (e.g., in comments or literals) could influence the agent's logic.
- Ingestion points: The skill reads source files (e.g., src/lib.rs, src/main.rs) and project metadata using the Read and LSP tools as defined in the refactoring workflows.
- Boundary markers: There are no explicit delimiters or instructions to the agent to ignore or treat content within the ingested files as untrusted data.
- Capability inventory: The skill utilizes the Edit tool to apply changes to the filesystem, and the Glob and Grep tools for code discovery.
- Sanitization: No validation, filtering, or sanitization of the ingested code content is performed before the agent processes it to determine refactoring steps.
Audit Metadata