brand-research
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes Step 4–4.5 “Winning-content sweep” that scrapes Instagram keyword search results and pulls transcripts/captions from outsider-authored posts (plus read-only Gmail/Slack text in Step 1), which the LLM ingests at runtime without selecting a specific item it authored first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata