career-navigator
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any malicious code, obfuscation, or unauthorized access patterns. All instructions and reference materials are aligned with the stated purpose of professional career coaching.
- [INDIRECT_PROMPT_INJECTION]: The skill performs active research by ingesting data from external sources, including web search results and user-provided screenshots of professional profiles. While this constitutes a surface for indirect prompt injection, the risk is assessed as minimal because the agent's capabilities are focused on data analysis and document generation within a restricted workspace, without access to sensitive system commands or credentials.
- [EXTERNAL_DOWNLOADS]: The skill references numerous well-known professional platforms and services (such as LinkedIn, Glassdoor, and various official UK/US recruitment and support organizations). These references are used legitimately for research and user guidance.
- [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were detected. The skill requests specific career-related information from the user (such as LinkedIn URLs or experience history) to provide personalized advice, which is a standard functional requirement. It stores preferences and output documents in localized workspace directories.
Audit Metadata