The Agent Skills Directory

[SAFE]: The skill is a set of instructions for context gathering in a Rust development environment. It defines a systematic way to read Cargo.toml and other metadata files to establish a project baseline.
[DATA_EXPOSURE]: The instructions involve reading local project files such as Cargo.toml, Cargo.lock, and source code. This is a standard and expected behavior for a developer-oriented agent tool and does not involve any unauthorized data access or network transmission.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local project repositories (source code and configuration files). While this presents a theoretical surface for indirect prompt injection, the skill is structured to extract metadata and patterns rather than executing the content, and no exploitable capabilities or unsafe interpolations are triggered by this process.

load-context