ultimate-rust
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to process untrusted local data from a user's codebase.
- Ingestion points: The skill targets project configuration and source files through the
globssetting inSKILL.md(specifically**/Cargo.tomland**/*.rs). - Boundary markers: The instructions do not include boundary markers or specific directives for the agent to ignore instructions embedded within the files being analyzed.
- Capability inventory: The skill empowers the agent to perform deep code analysis, architectural review, and error resolution, which are high-value targets for injection.
- Sanitization: There are no documented steps to sanitize or validate the content of the analyzed files for malicious directives before they are incorporated into the agent's context.
Audit Metadata