hung-yi-lee
Warn
Audited by Snyk on Jun 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). Runtime path: the skill’s workflow loads and uses cached YouTube transcript text from
raw/youtube/transcripts/*.md(outsider-authored public web content) into the agent’s LLM context via the knowledge-base search/graph query.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata