anthropic-expert

Warn

Audited by Snyk on Feb 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: 0.80). The skill explicitly describes using web search, the MCP connector and MCP servers (see references/mcp-integration-guide.md and the Tools section) and Files/API integrations (e.g., Slack, GitHub, Google Drive, public web search and uploaded PDFs) which cause the agent to fetch and read untrusted, user-generated third-party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:54 AM