The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and rewrites comments from external source files.
Ingestion points: Reads all files in the src/ directory or a user-provided path.
Boundary markers: Does not implement any delimiters or instructions to ignore embedded commands within the files.
Capability inventory: Executes rg and cargo clippy and modifies files iteratively without user confirmation.
Sanitization: No validation or sanitization of the comment content is performed before processing.
[COMMAND_EXECUTION]: The skill executes shell commands including rg and cargo clippy. Running cargo clippy on an untrusted codebase can lead to arbitrary code execution through the project's build scripts (build.rs) or procedural macros.

rewrite-rustdoc