bevy-ecs
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon project configuration files like Cargo.toml and Rust source code to provide accurate API guidance, which creates a surface where embedded instructions in those files could influence agent behavior.
- Ingestion points: Reads local project files including
Cargo.toml,Cargo.lock, and.rssource files. - Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions that might be contained within user-supplied code or configuration files.
- Capability inventory: The skill generates Rust code and suggests the use of the
cargo runterminal command. - Sanitization: There is no mention of sanitizing or escaping the content read from the external project files before processing.
- [COMMAND_EXECUTION]: The instructions suggest using
cargo runto build and debug the Bevy application, which involves executing code in the local environment.
Audit Metadata