rust-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes a suite of powerful development tools including
Bash,cargo,rustc, andmiri. These capabilities are essential for the primary purpose of Rust systems engineering. No evidence of malicious command assembly or unauthorized persistence was found. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection vulnerability (Category 8).
- Ingestion points: The agent is instructed to read
Cargo.toml, project dependencies, workspace structures, and source code files (viaRead,Grep,Glob). - Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent on how to safely distinguish between data to be processed and malicious instructions embedded in project files.
- Capability inventory: The agent has extensive capabilities including file system modification (
Write), arbitrary command execution (Bash), and compilation/execution of code (cargo,rustc). - Sanitization: No sanitization or validation of external project content is mentioned in the workflow.
Audit Metadata