modernizer
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface.
- Ingestion points: The agent is instructed to read and analyze the user's existing codebase, architecture, and tech stack in the 'Analyze Current State' and 'Document Features & Logic' steps of the workflow as described in SKILL.md and references/modernizer.md.
- Boundary markers: The instructions do not specify the use of delimiters or explicit 'ignore' instructions to separate agent directives from the untrusted data found within the processed codebase.
- Capability inventory: The skill utilizes the 'rg' (ripgrep) command for local searches and is explicitly designed to 'scaffold a new structure' by creating new directories and files (e.g., in a '/modernizedone/' directory) based on its analysis.
- Sanitization: There is no evidence of sanitization, validation, or filtering of the content extracted from the codebase before it is summarized or used to generate modernization plans and project scaffolds.
Audit Metadata