rust-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the local development environment which creates a potential surface for instructions embedded in code to influence agent behavior.
- Ingestion points: Project workspace files and Cargo configuration mentioned in SKILL.md.
- Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded content.
- Capability inventory: File modification (implementing solutions) and command execution (benchmarks, tests, MIRI).
- Sanitization: Absent; the skill is designed to process source code directly.
- [DYNAMIC_EXECUTION]: The skill is designed to execute code as part of its verification workflow.
- Evidence: The instructions include benchmarking performance-critical code, running comprehensive test coverage, and performing MIRI verification for unsafe blocks on local Rust source.
Audit Metadata