The Agent Skills Directory

[SAFE]: No malicious patterns or security violations were detected. The skill's instructions are focused on legitimate code review tasks using official toolchains.
[COMMAND_EXECUTION]: The skill utilizes shell commands like cargo test and cargo check to verify code correctness. While these commands can execute code from the project being reviewed (such as build.rs or test suites), this is a standard and necessary component of a Rust development workflow and is the primary purpose of this skill.
[PROMPT_INJECTION]: The skill acts as an indirect prompt injection surface because it is designed to ingest and analyze untrusted repository code and instructions. However, this is an inherent property of automated code review tools.
Ingestion points: Changed files, repository manifests, and repository instructions referenced in SKILL.md.
Boundary markers: Absent; there are no specific delimiters instructing the agent to ignore instructions embedded within the code diffs.
Capability inventory: Execution of git and cargo commands as specified in the Workflow section of SKILL.md.
Sanitization: Absent; the skill relies on the agent's internal safety filters and the user's provision of the review context.

rust-code-review