mph-voice-refresh
Warn
Audited by Snyk on Jun 18, 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). Outsider free text can enter the LLM context via
scripts/mine_feed.pyfetching and parsing the public Substack RSS feed (https://mphinance.substack.com/feed) at runtime, then emitting scraped post text as candidate openers/closers/sentences for the agent to review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata