gifhorse
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the tool to "download subtitles from online providers" by default when running "gifhorse transcribe", meaning it fetches and ingests untrusted public subtitle files (third-party/user-generated) that the agent reads and uses for search/clip creation, which could allow indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata