Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Brave Search integration that sends search terms and a Brave API key to Brave's search API, which matches its stated purpose.
Install only if you are comfortable sending your search queries to Brave Search and providing a Brave API key through BRAVE_API_KEY. Do not include secrets, private customer data, or confidential internal details in search queries.
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
try:
req = urllib.request.Request(url, headers=headers)
with urllib.request.urlopen(req) as response:
if response.status == 200:
data = json.loads(response.read().decode())
results = []
The skill advertises executable behavior that uses environment variables and network access, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens reviewability and containment because users and platforms cannot easily see or enforce what capabilities the skill needs before installation or invocation.
The skill description and usage text do not clearly warn that user queries will be transmitted to Brave's external search service. Without an explicit disclosure, users may provide sensitive prompts or identifiers that are then sent off-platform, creating privacy and compliance risk.
The usage guidance is very broad: 'search for anything' could cause the agent to invoke the skill in many contexts without clear user intent or guardrails. Over-broad triggering increases the chance of accidental data disclosure in queries and unnecessary calls to an external service.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# Brave Search API Configuration
# Reads from environment variable BRAVE_API_KEY
API_KEY = os.getenv("BRAVE_API_KEY")
BASE_URL = "https://api.search.brave.com/res/v1/web/search"
def search_brave(query, count=5):
if not API_KEY:
User-supplied search queries are sent to an external third-party service, which can expose sensitive prompts, internal investigation topics, or personal data if users are unaware of the transmission. In a tool/skill context, this matters because queries may be constructed from broader agent context and not just explicit user text, increasing privacy and data-handling risk.
No suspicious patterns detected.