rust-testing-quality
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and test local Rust codebases. This creates a surface for indirect prompt injection if the codebase being analyzed contains malicious instructions disguised as code or comments.\n
- Ingestion points: The agent reads the local codebase using
fuse-ai-pilot:explore-codebase(as specified inSKILL.md).\n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the analyzed code.\n
- Capability inventory: The skill utilizes shell execution for
cargo nextest,cargo test,cargo bench, andcargo mutants(found inSKILL.md,references/test-organization.md,references/property-and-mutation.md).\n - Sanitization: No explicit sanitization or validation of the codebase content is performed before execution.\n- [COMMAND_EXECUTION]: The skill relies on executing various
cargocommands to perform testing, benchmarking, and mutation analysis. While these are standard development tools, they execute code from the project environment.
Audit Metadata