mock-interview

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content from multiple local YAML files which may contain untrusted or externally-influenced data, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads from search/context/experience-library.yaml, search/context/interview-answers.yaml, search/intel/{company-slug}.yaml, and search/context/interview-history.yaml.
  • Boundary markers: No delimiters or explicit instructions to disregard embedded commands within the ingested files are present.
  • Capability inventory: The agent has access to Bash, Write, Edit, and blackboard communication tools, which could be misused if a prompt injection attack were successful.
  • Sanitization: The skill does not perform any validation or sanitization of the file content before it is processed by the AI model.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 05:36 AM
Security Audit — agent-trust-hub — mock-interview