The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs code analysis by executing local cargo commands. Evidence: modules/cargo-dependencies.md instructs the agent to run cargo tree -d, cargo audit, cargo outdated, and cargo deny check to analyze dependencies and security vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill initiates downloads of security advisories from established services. Evidence: The cargo audit command in modules/cargo-dependencies.md fetches the RustSec advisory database, which is a well-known and expected service for this audit function.
[PROMPT_INJECTION]: The skill's architecture is vulnerable to indirect prompt injection because it processes external code. Ingestion points: Rust source code and 'Cargo.toml' files analyzed in 'SKILL.md' and modules. Boundary markers: No explicit isolation or instructions for the agent to ignore embedded instructions in analyzed content. Capability inventory: Execution of cargo CLI tools for project analysis. Sanitization: No sanitization of the untrusted code inputs is performed before processing.

rust-review