The Agent Skills Directory

[SAFE]: The skill consists of technical documentation and code snippets intended to guide an AI in generating high-quality Rust code. It does not perform any autonomous actions, network operations, or file modifications.- [COMMAND_EXECUTION]: The skill includes patterns for interacting with subprocesses using std::process::Command. These examples correctly emphasize security best practices, such as capturing stderr for context, handling non-UTF-8 output, and implementing execution timeouts to prevent resource exhaustion.- [INDIRECT_PROMPT_INJECTION]: The guide advocates for a 'Conservative by Default' posture, instructing the agent to treat all external inputs as untrusted and to use strict validation patterns (e.g., Serde's deny_unknown_fields).- [CREDENTIALS_UNSAFE]: No hardcoded credentials or sensitive tokens are present in the provided reference files. Placeholders are used in configuration examples.- [OBFUSCATION]: No malicious encoding or hidden data was found. Use of specific Unicode characters (like the BOM) is appropriate within the context of text-parsing documentation.

rust