unify-design
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes common development utilities including git grep, git log, stylelint, and eslint for auditing codebases. These operations are scoped to the project environment and are used for their intended purposes.
- [EXTERNAL_DOWNLOADS]: Interacts with recognized package managers such as npm, pnpm, yarn, and bun for dependency management. These are well-known and trusted services.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it ingests untrusted code from project source files while maintaining capabilities to write files and execute commands.
- Ingestion points: Local source files located in src/, app/, components/, and styles/ directories.
- Boundary markers: No specific boundary markers or 'ignore' instructions are used when processing local files.
- Capability inventory: Includes file system write/edit access and the execution of package manager shell commands.
- Sanitization: Relies on regex pattern matching and manual classification of findings.
Audit Metadata