improve-code-quality
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard Rust toolchain commands (
cargo check,cargo clippy,cargo fmt,cargo nextest) to perform automated audits and apply fixes. These are intended behaviors for a code quality skill. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes source files in the repository, creating a surface where malicious content in those files (e.g., instructions in comments) could attempt to manipulate the agent's reporting or fix suggestions.
- Ingestion points: Reads source files (e.g., Rust
.rsfiles,Cargo.toml) and directory structures within the monorepo. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat file content purely as data and ignore any embedded natural language instructions.
- Capability inventory: The agent has the ability to run shell commands (via cargo) and modify files (during the fixing phase in Step 5).
- Sanitization: The skill does not describe any sanitization or validation of the code content before it is processed by the LLM for manual analysis or report generation.
Audit Metadata