rust-api-test-harness
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a shell script
scripts/check-rust-service.shthat executes standard Rust toolchain commands (cargo fmt,cargo clippy, andcargo test). These are intended for verifying code quality and correctness in a development environment. - [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze existing project files (such as
Cargo.toml, source code, and migrations) to generate integration tests. This ingestion of local project content represents an attack surface for indirect prompt injection. - Ingestion points: Core Workflow instructions in
SKILL.mdguide the agent to readCargo.toml,src/,tests/, migrations, and CI workflows. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat the analyzed code as untrusted data.
- Capability inventory: The skill utilizes a shell script to execute
cargo test, which runs compiled code from the project. - Sanitization: No sanitization or validation of the ingested code is performed before analysis.
Audit Metadata