The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Rust source code and Cargo projects, which presents a surface for indirect prompt injection attacks.\n- Ingestion points: Rust source code, workspace files, and Cargo manifest metadata (SKILL.md).\n- Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between user instructions and instructions potentially embedded in code comments or documentation within the processed files.\n- Capability inventory: The agent is empowered to modify files (Rust edits) and execute shell commands related to building and testing code, such as cargo test, cargo clippy, and cargo fmt (references/style-and-design.md).\n- Sanitization: There are no instructions for sanitizing or validating the content of the source code or comments being handled by the agent.

ferris-rust