job-application
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- PROMPT_INJECTION (LOW): Vulnerable to indirect prompt injection (Category 8). Ingestion points: Untrusted job descriptions provided by users as noted in SKILL.md. Boundary markers: None. Capability inventory: Text generation and formatting (no command execution or network access). Sanitization: None detected.
- DATA_EXFILTRATION (LOW): Potential for data exposure (Category 2). The skill prompts for sensitive PII including CVs, LinkedIn, and Portfolio links. While no exfiltration logic is present, the storage of PII within the agent's prompt context is a risk factor.
Audit Metadata