The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and provide feedback on user-supplied Rust code snippets, which creates a potential surface for indirect prompt injection if malicious instructions are embedded in the analyzed code.
Ingestion points: User-provided Rust traits, implementations, and compiler error messages as described throughout SKILL.md and the references/ files.
Boundary markers: None; the skill instructions do not define specific delimiters or instructions for the agent to ignore commands that may be contained within the code it analyzes.
Capability inventory: The skill is compatible with Claude Code, which has extensive capabilities including shell execution, filesystem access, and tool invocation.
Sanitization: None; there are no instructions provided to sanitize, escape, or validate the content of the user-supplied Rust snippets before they are processed by the agent.

rust-syntax-gats