rust-refactor-helper
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted data from local source files.
- Ingestion points: The skill ingests data from local files using the
Read,Glob, andGreptools to analyze Rust source code. - Boundary markers: No specific delimiters or boundary instructions are used to distinguish between the agent's internal instructions and the content being read from the files.
- Capability inventory: The skill is granted the
Edittool, allowing it to modify files on the filesystem based on the analysis of the ingested data. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content read from files to prevent the execution of instructions that might be embedded within code comments or strings.
Audit Metadata