using-rust-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external Rust source code and Cargo manifests, creating a surface where malicious instructions embedded in a codebase could influence the agent's actions.\n
- Ingestion points: The instructions in
SKILL.mdandproject-structure-and-tooling.mddirect the agent to ingest and analyze user-provided Rust source files,Cargo.tomlmanifests, and build configuration files.\n - Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions within the processed source code, increasing the risk of the agent following instructions found in the data.\n
- Capability inventory: The skill leverages powerful capabilities including executing
cargo check,cargo test,clippy,rustc, and various profiling and auditing tools as described inSKILL.mdandtesting-and-quality.md.\n - Sanitization: There are no instructions for sanitizing or filtering content from external files before the agent processes them or uses them as arguments for local command execution.
Audit Metadata