tailrocks-rust-review
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard Rust toolchain commands such as
cargo test,cargo clippy,cargo bench,cargo doc, andcargo flamegraph, along with themisetask runner for code analysis and verification. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Rust source code and repository data, creating a potential attack surface.
- Ingestion points: Rust source files and repository diffs provided as review targets.
- Boundary markers: The skill includes a
runtime-trust.mdreference that explicitly instructs the agent to treat repository content as untrusted and ignore embedded instructions. - Capability inventory: The skill can execute code via
cargo test,cargo bench, andmise run. - Sanitization: Explicit prompt instructions mandate read-only filesystem access, network isolation, and authorization before any command execution.
Audit Metadata