marketing-social
Warn
Audited by Snyk on Mar 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Research Mode in SKILL.md explicitly directs the agent to use agent-browser to open and scrape live public third-party pages (e.g., "https://www.instagram.com/{competitor-handle}/", "https://www.tiktok.com/@{competitor-handle}", "https://www.linkedin.com/company/{competitor-linkedin}/") and to extract text/screen content for competitive analysis, which clearly ingests untrusted user-generated web content that can influence agent decisions and actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's Research Mode requires installing and running the agent-browser package via the runtime fetch command "npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser" which downloads and executes remote code from that GitHub URL and is a required dependency for browser-based operations.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata