byted-recruitment-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes data from external job description files (jd-process/*) and candidate records (data/candidates-[日期].md). Boundary markers and explicit sanitization logic are absent in the instructions. However, the capability inventory is restricted to reading these local files and writing markdown reports to the data/hiring-reports/ directory. No network operations, arbitrary command execution, or other high-risk capabilities were identified, making this surface safe within the intended reporting context.
Audit Metadata