ClawHub
Back to skill

Security audit

Vision Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently sends user-selected images to Ollama Cloud for analysis and does not show hidden persistence, unrelated data access, or destructive behavior.

Install only if you are comfortable sending the chosen image and prompt to Ollama Cloud. Avoid using it on sensitive screenshots, private documents, regulated data, or images you do not have permission to upload.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tainted flow: 'req' from os.environ.get (line 53, 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/vision_analyze.py (reported line 57)May include surrounding context.

python
# Send request
    try:
        with urllib.request.urlopen(req, timeout=120) as response:
            result = json.loads(response.read().decode('utf-8'))
            return result.get("response", "No response field found")
    except urllib.error.HTTPError as e:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes a Python script that relies on environment variables and sends data to a remote Ollama Cloud API, yet the manifest declares no explicit tool scope or permissions. This creates a transparency and control gap: users and policy engines cannot easily tell that the skill can access secrets from the environment and transmit image content over the network.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation presents the skill as an image analyzer but does not clearly warn at the point of use that supplied images are uploaded to a cloud service for processing. Users may provide screenshots, documents, or other sensitive images under the assumption of local analysis, resulting in unintended disclosure of private or regulated data to a third party.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.