The Agent Skills Directory

[SAFE]: The skill consists of documentation and procedural steps for porting code between languages. It promotes secure development practices such as using locked dependencies and automated testing.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external, untrusted source code. Ingestion points: The agent is instructed to read the original source code, its tests, and its callers (SKILL.md). Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the source code. Capability inventory: The workflow involves executing cargo test and cargo clippy, which perform code compilation and execution. Sanitization: No specific sanitization or escaping of the input source code is required. This represents a known attack surface for indirect prompt injection, but it is considered a safe finding as it is inherent to the skill's primary function of code porting.

rust-port