The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and optimize user-provided Rust source code, which serves as an ingestion point for untrusted data. * Ingestion points: The skill description and audit checklists indicate the agent will process user Rust code snippets and performance-related queries as described in SKILL.md. * Boundary markers: The instructions do not explicitly define delimiters or provide warnings for the agent to ignore potentially malicious instructions embedded within the user's code. * Capability inventory: The skill body in SKILL.md mentions the use of external profiling and analysis tools such as cargo-show-asm, perf, samply, and hyperfine. * Sanitization: The instructions do not specify any validation or sanitization steps for the data processed during the audit.
[SAFE]: The skill consists of high-quality, purely instructional content focused on Rust programming best practices and performance optimization.
[SAFE]: The skill demonstrates security awareness by recommending against the use of unmaintained packages with known vulnerabilities, specifically referencing the bincode advisory RUSTSEC-2025-0141 in references/tokio-ecosystem.md.
[SAFE]: All external libraries and tools referenced (e.g., tokio, serde, rayon, Criterion) are legitimate, widely-used components of the Rust ecosystem.

rust-high-performance