youtube-for-ai
Warn
Audited by Snyk on Jun 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: 0.95). The required workflow uses Stophy CLI to fetch YouTube transcripts/comments/live chat at runtime (e.g.,
stophy video transcript --url ...,stophy video comments --url ...,stophy video livechat --url ...), which ingests outsider-authored free text (video spoken content, user comments, chat messages) into the agent’s LLM context.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill instructs runtime use of "npx @stophy/cli", which fetches and executes remote code from the npm registry at runtime (i.e., an external dependency the skill relies on that can execute remote code), so it presents a runtime external-execution dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata