bevy
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to perform standard software development tasks using the Rust toolchain, including
cargo build,cargo check, andcargo tree. These commands are used to compile the project, verify syntax, and inspect dependencies.\n- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided project code and assets, creating a potential surface for indirect prompt injection if those files contain malicious instructions aimed at the agent.\n - Ingestion points: Local project source code, configuration files (Cargo.toml), and asset files referenced during the development process.\n
- Boundary markers: No specific delimiters or "ignore instructions" wrappers are defined for the code being analyzed or processed.\n
- Capability inventory: The skill utilizes shell command execution capabilities (
cargocommands) and file system read access to registry examples and project files.\n - Sanitization: The instructions do not specify any validation or sanitization steps for the ingested code before processing or execution.
Audit Metadata