cold-start-interview

Warn

Audited by Snyk on Jul 9, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The required workflow in SKILL.md runs an “Interview the accountant/partner” and uses their responses to scaffold/write firm-profile.md and CLAUDE.md, so outsider-authored free text from the partner/accountant is ingested into the agent’s LLM context during the interview.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 9, 2026, 02:13 PM
Issues
1
Security Audit — snyk — cold-start-interview