rust-performance

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and suggest optimizations for user-provided Rust code, which introduces an attack surface for indirect prompt injection. Ingestion points: The agent processes user-supplied Rust source code as part of its optimization and review workflows. Boundary markers: The instructions do not specify explicit delimiters or guardrails to distinguish between user code and embedded instructions. Capability inventory: The skill utilizes local development and profiling utilities including 'cargo' (test, bench, clippy), 'perf', 'valgrind', and 'numactl'. Sanitization: There are no instructions for sanitizing or validating user-provided code before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:35 AM