The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze, review, and debug external Rust source code and project structures, which creates a surface where untrusted data is ingested into the agent's context.
Ingestion points: The skill reads local Rust source files (.rs), project configuration files (Cargo.toml), and user-supplied code snippets for the purpose of debugging and code review as described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted code from the agent's internal instruction set.
Capability inventory: The skill utilizes standard Rust development tooling via the shell, including cargo test, cargo clippy, cargo bench, and cargo fmt. cargo test and cargo bench involve the execution of the code under analysis, which is a significant capability if the code is malicious.
Sanitization: The skill does not specify any sanitization, escaping, or validation steps for handling external code before processing or executing tests.

rust-engineer