Back to skill

Security audit

EmpirioLabs AI OCR

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this OCR skill suspicious because a confirmed redirect issue could expose its API key, while some scanner checks were incomplete.

Consider the API-key redirect weakness and the missing tool-scope declaration before installing. The scanner inspected all three listed components, but analysis was marked partial because several local references could not be resolved, so the evidence is incomplete.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Automatic redirects can send the API key to a non-EmpirioLabs host, contradicting the documented credential restriction.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The code checks the initial URL before attaching Authorization, but urllib.request.urlopen follows redirects and can carry that header to a different host without repeating the check. If an authenticated API response redirects to an attacker-controlled destination, the API key could be exposed and used for unauthorized API access or billable requests; this requires control over or influence on such a redirect.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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/empiriolabs_api.py (reported line 29)May include surrounding context.

python
__version__ = "1.0.0"

API_BASE = "https://api.empiriolabs.ai/v1"
KEY_ENV = "EMPIRIOLABS_API_KEY"
KEYS_URL = "https://platform.empiriolabs.ai/dashboard/api-keys"
BILLING_URL = "https://platform.empiriolabs.ai/dashboard/billing"

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · scripts/empiriolabs_api.py (reported line 352)May include surrounding context.

python
def list_models(timeout=60.0):
    """The public model catalog. No API key is needed."""
    payload = get_json("/models", auth=False, timeout=timeout)
    models = payload.get("data") if isinstance(payload, dict) else payload
    return models if isinstance(models, list) else []

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · scripts/empiriolabs_api.py (reported line 360)May include surrounding context.

python
def get_model(model_id, timeout=60.0):
    """One catalog entry, or None when the catalog has no entry with that id."""
    try:
        return get_json("/models/" + urllib.parse.quote(model_id, safe=""), auth=False, timeout=timeout)
    except ApiError as exc:
        if exc.status == 404:
            return None