The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions attempting to bypass safety filters, override behavior, or extract system prompts were detected. The language is purely instructional and focused on Rust development.
[DATA_EXFILTRATION] (SAFE): The skill does not access sensitive user files or perform unauthorized network requests. Interaction with project files like Cargo.toml and Cargo.lock is standard for Rust dependency management.
[REMOTE_CODE_EXECUTION] (SAFE): No patterns of downloading and executing remote scripts (e.g., curl | bash) were found. All referenced URLs point to trusted official Rust community resources.
[COMMAND_EXECUTION] (LOW): The skill documentation includes standard shell commands for rustup and cargo. These are intended for user-initiated execution and follow industry best practices for environment management.
[INDIRECT_PROMPT_INJECTION] (LOW): While the skill specifies globs to ingest project metadata (**/*.toml), it lacks automated executable capabilities in the provided source that could be leveraged for an injection attack. The capability tier is primarily informational.

rust-learner