dev-rust
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and refactor Rust source code from external repositories, creating a surface where malicious instructions could be embedded in code comments or data files.
- Ingestion points: The skill reads local Rust source files, Cargo workspace manifests (Cargo.toml), and toolchain configurations as specified in SKILL.md and references/checklist.md.
- Boundary markers: Instructions emphasize grounding the agent's actions in existing repository guidance and worktree state, though no explicit delimiters are mandated for the ingested content itself.
- Capability inventory: The skill utilizes file system access (read/write) and execution of toolchain commands such as cargo build, cargo test, and clippy.
- Sanitization: While the skill lacks explicit sanitization for ingested prompt data, it contains extensive defensive guidelines for the AI to implement robust input validation within the generated Rust code.
Audit Metadata