setup

Fail

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: CRITICALPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources such as resumes and LinkedIn CSV exports, creating a surface for indirect prompt injection.
  • Ingestion points: Data is ingested from user-provided resumes in DATA_DIR/resume/ and contact exports in DATA_DIR/linkedin-contacts.csv (referenced in SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific markers to prevent the model from obeying instructions that might be embedded within the ingested resume or contact files.
  • Capability inventory: The skill is designed for local data management and conversational interviewing; it does not utilize subprocess execution, dynamic code evaluation, or network-enabled tools in the provided scripts.
  • Sanitization: No evidence of sanitization or content filtering was found for the data read from external files before it is processed into the work history profile.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 25, 2026, 03:47 AM