ln-711-npm-upgrader

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the worker to query external documentation and web search (see "Phase 4: Identify Breaking Changes" and "MCP Tools for Migration Search" using mcp__context7__query-docs, mcp__Ref__ref_search_documentation / mcp__Ref__ref_read_url and a WebSearch fallback that reads public URLs/StackOverflow) and to fetch migration guides which are then used to decide and apply migrations, so untrusted third‑party content can influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 05:53 AM