israeli-job-market
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information, such as CV content and job requirements, to provide optimization and career guidance. This creates a potential surface for indirect prompt injection where instructions embedded in a user's resume could attempt to influence agent behavior.
- Ingestion points: User-provided CV text and job search parameters are processed within the agent context in
SKILL.mdandSKILL_HE.md. - Boundary markers: The skill does not define specific delimiters or guardrails to isolate user-supplied content from its own instructions.
- Capability inventory: The skill utilizes the
WebFetchtool to retrieve data from external recruitment and salary platforms. - Sanitization: No explicit sanitization or filtering of user-provided content is performed before processing.
- [EXTERNAL_DOWNLOADS]: The skill references and encourages the use of several external platforms and MCP servers for live data retrieval.
- Evidence: The skill recommends the use of the
Israeli CBS MCPandKolzchut MCPhosted atagentskills.co.il. It also refers to official Israeli government domains (cbs.gov.il,btl.gov.il,ejobs.gov.il) and established industry portals (levels.fyi,geektime.co.il,alljobs.co.il). These resources are well-known services or vendor-affiliated tools and are documented here for transparency.
Audit Metadata