interview-designer
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes resumes, which are untrusted external data sources. This introduces a vulnerability to indirect prompt injection where an attacker (candidate) could include malicious instructions within the resume to bias the AI's evaluation or bypass the 'Objective Evaluator' constraints.
- Ingestion points: The skill scans resumes in 'Step 2: Forensic Resume Scan' as defined in SKILL.md.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the resume data.
- Capability inventory: The skill's capabilities are limited to generating structured text output (interview guides) and does not show evidence of file system modification, network exfiltration, or code execution.
- Sanitization: The skill lacks explicit sanitization or validation logic for the content of the resumes it processes.
Audit Metadata