ClawHub
Back to skill

Security audit

Tavily Search with Multi-Key

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Tavily web-search helper; it sends search queries and the configured Tavily API key to Tavily, which is expected for its purpose.

Install only if you are comfortable sending search queries to Tavily and storing a Tavily API key in environment variables or ~/.openclaw/.env. Avoid using it for secrets, private internal URLs, or proprietary text unless that data is allowed to leave your environment.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (10)

Tainted flow: 'req' from os.environ.get (line 102, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
method="POST",
    )

    with urllib.request.urlopen(req, timeout=30) as resp:
        body = resp.read().decode("utf-8", errors="replace")

    try:
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Credential Access

High
Category
Privilege Escalation
Content
# 支持多 key 轮询：TAVILY_API_KEYS=key1,key2,key3
def _load_keys():
    """从环境变量或 .env 文件加载多 key"""
    keys_str = os.environ.get("TAVILY_API_KEYS", "")
    if keys_str:
        return [k.strip() for k in keys_str.split(",") if k.strip()]
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
if keys_str:
        return [k.strip() for k in keys_str.split(",") if k.strip()]

    env_path = pathlib.Path.home() / ".openclaw" / ".env"
    if env_path.exists():
        try:
            txt = env_path.read_text(encoding="utf-8", errors="ignore")
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
if keys_str:
        return [k.strip() for k in keys_str.split(",") if k.strip()]

    env_path = pathlib.Path.home() / ".openclaw" / ".env"
    if env_path.exists():
        try:
            txt = env_path.read_text(encoding="utf-8", errors="ignore")
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
if keys_str:
        return [k.strip() for k in keys_str.split(",") if k.strip()]

    env_path = pathlib.Path.home() / ".openclaw" / ".env"
    if env_path.exists():
        try:
            txt = env_path.read_text(encoding="utf-8", errors="ignore")
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill invokes a Python script that uses environment variables, reads a user home directory config file, and performs outbound network requests, yet the manifest declares no explicit tool scope or allowed-tools restrictions. This weakens least-privilege controls and can cause the skill to be granted broader capabilities than users or orchestrators expect, increasing the blast radius if the script is modified or abused.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description says to use the skill when the user asks to "search the web / look up sources / find links," which are broad natural-language triggers without tighter scope or exclusion conditions. Because no negative examples or narrower activation boundaries are provided, this could cause unintended invocation in loosely related conversations.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The requirements section uses Chinese-only instructional text ("多 key 轮询（推荐）" and "单 key 模式") while the rest of the file is in English, which imposes a language inconsistency without opt-in or documented rationale. This can violate language/locale policy expectations where the skill should not force or assume a specific language unexpectedly.

External Transmission

Medium
Category
Data Exfiltration
Content
import sys
import urllib.request

TAVILY_URL = "https://api.tavily.com/search"

# 支持多 key 轮询：TAVILY_API_KEYS=key1,key2,key3
def _load_keys():
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill sends user search queries and an API credential to a third-party service without any in-code notice, consent check, or data-sensitivity guard. In an agent setting, users may provide secrets, internal URLs, or proprietary text in a query, and this code will forward that content externally by design.

Static analysis

No suspicious patterns detected.