fast-rust
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for standard Rust toolchain operations including
cargo build,rustup component add, and the use of thellvm-profdatautility. These are standard engineering practices for performance measurement and Profile-Guided Optimization (PGO). - [EXTERNAL_DOWNLOADS]: The skill references technical documentation and blog posts from
databend.com,fast.github.io, and GitHub. These external resources provide legitimate technical context for the engineering patterns described. - [PROMPT_INJECTION]: The skill is designed to process and review Rust source code, which creates a surface for indirect prompt injection if malicious instructions are embedded in the code or comments provided to the agent.
- Ingestion points: Rust source code files (.rs) and code snippets.
- Boundary markers: No explicit delimiters or isolation instructions are provided.
- Capability inventory: The skill guides the agent to perform command-line build operations and configuration changes.
- Sanitization: No sanitization of user-provided code is specified.
Audit Metadata