creator-triage

Warn

Audited by Snyk on Jun 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.75). Creator triage reads outsider-authored free text from Paperclip issue fields—especially comments and description/plan content authored by other users—via the required runtime step “Read the target issue or issue list” (Paperclip control-plane records are ingested into the agent’s LLM context for classification and recommendations).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running npx to fetch-and-execute the MCP server package (npx -y @bbengamin/paperclip-mcp-server — https://www.npmjs.com/package/@bbengamin/paperclip-mcp-server), which downloads and runs remote code at runtime and is relied on as a required fallback for Paperclip operations.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 16, 2026, 01:15 PM
Issues
2
Security Audit — snyk — creator-triage