The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content such as repository instructions and code diffs, creating a surface for injection attacks.
Ingestion points: SKILL.md instructs the agent to inspect repository instructions, changed files, surrounding symbols, and manifests.
Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions found within the analyzed files.
Capability inventory: The skill has the ability to execute shell commands via git and cargo.
Sanitization: No sanitization of the processed code or manifest data is performed.
[COMMAND_EXECUTION]: The skill workflow includes the execution of shell commands for repository analysis.
Evidence: SKILL.md explicitly lists commands such as git diff --check, cargo metadata, cargo check, cargo test, and cargo clippy.
Context: These commands are part of the standard Rust development toolchain and are used as intended for code verification and linting.

rust-code-review