The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation, checklists, and best-practice rules for Rust programming. No security issues were detected across any of the analyzed threat categories.
[COMMAND_EXECUTION]: While the skill references many command-line tools (like cargo miri, bindgen, cbindgen) and C-style system calls in its documentation/examples, these are for educational purposes and are not executed by the skill itself.
[DATA_EXFILTRATION]: No network access or data transmission patterns were identified. The allowed tools (Read, Grep, Glob) are restricted to local file system inspection.
[PROMPT_INJECTION]: The skill instructions do not contain any attempts to override system prompts or bypass safety guardrails. Its primary purpose is to enhance the agent's ability to perform safety audits on user-provided Rust code.

unsafe-checker