mcp-api-build
Warn
Audited by Snyk on Aug 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill’s workflow describes building MCP/REST server patterns but the only runtime LLM-ingestible text shown is user-provided tool arguments (e.g.,
search_knowledge(query)), not first-party outsider-written content selected without the agent choosing a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata