marketing-community
Warn
Audited by Snyk on Aug 3, 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). The skill’s runtime workflow is “community building or management work” and it explicitly relies on reading the user-provided “live community URL”/repo and brand context files, i.e., it can ingest outsider-authored free text from a user-supplied live website/codebase at runtime.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's shared patterns include a runtime installation command that fetches and installs remote code from https://github.com/vercel-labs/agent-browser (npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser), which would execute third-party code during runtime to control browser-based research.\reason> 0.9 <unverifiable_urls> https://github.com/vercel-labs/agent-browser </unverifiable_urls>
references/shared-patterns.md:33-39
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata