mcp-cli
Warn
Audited by Snyk on Apr 8, 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). This skill's SKILL.md explicitly describes interacting with external systems such as "GitHub, filesystems, databases, and APIs" and shows workflow/commands (e.g., mcp-cli /, filesystem/read_file, filesystem/search_files, server/tool) that fetch and ingest third-party content which the agent is expected to read and could influence subsequent tool calls, so untrusted web/user-generated data can indirectly inject instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata