game-localization-manager
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to audit and process external codebase content, which introduces a surface for indirect prompt injection. * Ingestion points: The agent uses Read, Glob, and Grep tools to scan project source code and string tables during i18n audits (SKILL.md). * Boundary markers: Delimiters or 'ignore embedded instructions' warnings are absent. * Capability inventory: Subprocess calls via Bash, file-write, and editing capabilities are available across the workflow. * Sanitization: Escaping, validation, or filtering of external content is not explicitly instructed.
Audit Metadata