answers

Fail

Audited by Runlayer on Feb 22, 2026

Risk Level: HIGH
Scan Summary
Max Score
93%
Files
1
Flagged
1
Chunks
2
Flagged Files (1)
SKILL.mdHIGH
93.4%

Malicious tool definition detected

## Quick Start (cURL) ### Blocking (Single-Search) ```bash curl -X POST "https://api.search.brave.com/res/v1/chat/completions" \ -H "Content-Type: application/json" \ -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \ -d '{ "messages": [{"role": "user", "content": "How does the James Webb Space Telescope work?"}], "model": "brave", "stream": false }' ``` ### Streaming with Citations (Single-Search) ```bash curl -X POST "https://api.search.brave.com/res/v1/chat/completions" \ -H "Content-Type:

Tool: SKILL.md [2/2] Description: with web-grounded answers.

Audit Metadata
Max File Score
93%
Classification
UNKNOWN_SERVER
Files Scanned
1
Files Flagged
1
Chunks Analyzed
2
Analyzed
Feb 22, 2026, 02:35 PM
Security Audit — runlayer — answers