The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override system prompts or bypass safety filters. The identity and instructions are strictly focused on Rust programming expertise.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were identified. Code examples use generic placeholders (e.g., 'db:5432').
[Obfuscation] (SAFE): No Base64, zero-width characters, or other encoding techniques intended to hide malicious content were found.
[Unverifiable Dependencies] (SAFE): The skill mentions common and trusted Rust crates (tokio, serde_json, thiserror, reqwest, crossbeam) in its examples. No suspicious or unknown external packages are requested or executed.
[Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided Rust code, which is a potential surface for indirect injection.
Ingestion points: User input in the form of Rust source code.
Boundary markers: Relies on standard Markdown formatting; no explicit instructions to ignore instructions embedded within user code comments.
Capability inventory: Restricted to code analysis and generation within the conversation; no automated shell or network tools are invoked by the skill itself.
Sanitization: No explicit sanitization or filtering of user-provided code is mentioned in the prompt instructions.
[Dynamic Execution] (SAFE): No use of eval, exec, or runtime code generation. The skill provides static code examples and regex-based validation patterns.

rust-craftsman