jobhunter
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted job description text from external platforms (LinkedIn, Indeed, etc.) to generate tailored application materials.\n
- Ingestion points: Job descriptions extracted via browser automation in
SKILL.md.\n - Boundary markers: Absent. No delimiters or specific instructions to ignore embedded commands are present in the provided templates or logic.\n
- Capability inventory: The skill has access to browser automation (
Bash), email sending (MCP(gmail)), and spreadsheet management (MCP(google-sheets)).\n - Sanitization: Absent. The skill does not perform sanitization of external content before processing it for prompt generation.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes official Model Context Protocol (MCP) servers (
@modelcontextprotocol/server-google-sheetsand@modelcontextprotocol/server-gmail) from a well-known service to enable spreadsheet and email capabilities.
Audit Metadata