ClawHub
Back to skill

Security audit

Tavily Metered Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Tavily web-search helper that sends searches to Tavily and keeps a local monthly usage counter.

Install only if you are comfortable sending search queries and your Tavily API key to Tavily. Keep sensitive or private content out of search queries, and review the local usage counter if quota tracking matters to you.

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 (8)

Tainted flow: 'req' from os.environ.get (line 219, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/tavily_search.py (reported line 226)May include surrounding context.

python
method="POST",
    )

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

    try:

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/tavily_search.py (reported line 18)May include surrounding context.

python
Configuration:
  - Config file: {skill_dir}/config/config.json
  - Usage tracking: {skill_dir}/data/tavily-usage.json
  - API key: ~/.openclaw/.env (TAVILY_API_KEY)
"""

import argparse

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/tavily_search.py (reported line 86)May include surrounding context.

python
Configuration:
  - Config file: {skill_dir}/config/config.json
  - Usage tracking: {skill_dir}/data/tavily-usage.json
  - API key: ~/.openclaw/.env (TAVILY_API_KEY)
"""

import argparse

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/tavily_search.py (reported line 91)May include surrounding context.

python
if key:
        return key.strip()

    env_path = pathlib.Path.home() / ".openclaw" / ".env"
    if env_path.exists():
        try:
            txt = env_path.read_text(encoding="utf-8", errors="ignore")

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/tavily_search.py (reported line 205)May include surrounding context.

python
if key:
        return key.strip()

    env_path = pathlib.Path.home() / ".openclaw" / ".env"
    if env_path.exists():
        try:
            txt = env_path.read_text(encoding="utf-8", errors="ignore")

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill documentation declares required environment access and implies file read/write plus networked execution, but it does not define any explicit permission or allowed-tools scope. This creates an overbroad trust boundary where an agent may invoke a capability-rich skill without clear sandboxing constraints, increasing the chance of unintended file access, state modification, or outbound requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says to use this skill whenever the user asks to search the web, look up sources, or find links, which overlaps heavily with common natural-language requests. That broad trigger surface can cause the agent to invoke the skill in many contexts without strong user intent verification, sending user-provided queries to an external service and modifying local usage-tracking state.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/tavily_search.py (reported line 30)May include surrounding context.

python
import urllib.request
from datetime import datetime

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

# Default values (used when config file doesn't exist)
DEFAULT_CONFIG = {

Static analysis

No suspicious patterns detected.