Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Querit web-search integration that sends search queries and its configured Querit API key to Querit's API when invoked.
Install this only if you are comfortable giving the skill a Querit API key and sending your search queries or advanced JSON search payloads to Querit. Do not include passwords, tokens, private internal URLs, customer data, or other sensitive material in searches.
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
}
try:
response = requests.post(url, headers=headers, json=payload_data, timeout=30)
response.raise_for_status()
return json.dumps(response.json(), indent=2)
The skill invokes a Python script, requires an API key from the environment, and performs networked web searches, but it does not declare any explicit tool scope such as permissions or allowed-tools. That mismatch can cause the runtime or reviewers to underestimate the skill's capabilities, increasing the risk of unintended network access or environment-secret use.
The trigger conditions are broad enough to activate on many generic requests for current facts or news, which makes over-invocation likely. In a skill with network access and API-key usage, broad matching increases the chance of unnecessary external requests, data exposure through queries, or the skill being selected when a safer/local alternative would suffice.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
return json.dumps({"error": "QUERIT_API_KEY environment variable is missing. Please configure it in OpenClaw."})
# Replace with the actual Querit POST endpoint URL
url = "https://api.querit.ai/v1/search"
headers = {
"Authorization": f"Bearer {api_key}",
This code performs external network transmission of caller-controlled data to a third-party API. While expected for a web search skill, it still creates a real data-exposure boundary because any supplied payload is exported off-host, and in an agent environment that can leak sensitive prompt, user, or enterprise data if upstream controls are weak.
}
try:
response = requests.post(url, headers=headers, json=payload_data, timeout=30)
response.raise_for_status()
return json.dumps(response.json(), indent=2)
The script sends arbitrary user-provided query content directly to a third-party service without any disclosure, consent checkpoint, or data-sensitivity guardrails. In an agent skill context, users may unknowingly include secrets, internal URLs, or sensitive business data in queries, causing unintended external data exposure.