claude-prompting
Warn
Audited by Snyk on Feb 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill includes explicit examples and API snippets that enable and demonstrate web/tool searches (e.g., "tools=[web_search_tool]" in the Extended Thinking with Tools example and ReAct examples using <action_1>search), meaning the agent will fetch and ingest open web/search results (untrusted third-party content) as part of its workflow.
Audit Metadata