rust-development
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous commands using the Bash tool for the primary purpose of Rust development, including cargo build, cargo run, and cargo test. This grants the agent the ability to execute arbitrary commands and run compiled binaries on the host system.
- [EXTERNAL_DOWNLOADS]: The skill references standard Rust ecosystem operations such as adding dependencies via cargo add and installing helper tools via cargo install. These operations interact with the official crates.io registry.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection.
- Ingestion points: The agent is authorized to use WebFetch, WebSearch, and Read tools to ingest content from external files and the internet.
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following instructions embedded within the data it fetches.
- Capability inventory: The agent has significant system capabilities, including full Bash access, file writing (Write, Edit), and process management (KillShell).
- Sanitization: There are no built-in mechanisms described to sanitize or validate external content before it potentially influences agent behavior or is used in command execution.
Audit Metadata