skills/psiace/skills/fast-rust/Gen Agent Trust Hub

fast-rust

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): Reference file references/compilation-optimization.md contains instructions for using standard Rust development tools and shell commands like rm -rf and rustup. These are typical for Profile-Guided Optimization workflows.
  • EXTERNAL_DOWNLOADS (LOW): The skill metadata and reference files link to external documentation sites. These are purely informational and do not involve untrusted code execution.
  • PROMPT_INJECTION (LOW): The skill establishes an indirect prompt injection surface by processing user-provided Rust files. Mandatory Evidence Chain: 1. Ingestion points: .rs files and code snippets. 2. Boundary markers: Absent. 3. Capability inventory: Code generation, refactoring, and review. 4. Sanitization: Absent. This risk is common in AI-assisted development tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:02 PM