rust-copy-on-write
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to utilize standard development tools such as cargo clippy, cargo deny, cargo audit, and ripgrep (rg) for code verification and security auditing.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of user-provided Rust source code, which serves as an ingestion point for potentially untrusted data.
- Ingestion points: User source code processed during the "Verify the decision" and "Grep for the misuse" steps in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the analyzed code.
- Capability inventory: The skill assumes the ability to run shell commands including cargo (test, clippy, audit, deny) and rg.
- Sanitization: No specific sanitization or filtering of the analyzed code is performed before it enters the agent's context.
Audit Metadata