Back to skill

Security audit

doubao-image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Doubao image generator that uses a disclosed Volcengine API key and saves generated images, with manageable privacy and download-safety caveats.

Install only if you are comfortable sending prompts to Volcengine's Doubao API and using a VOLCENGINE_IMAGE_API_KEY in the environment. Avoid prompts containing secrets or regulated personal data, prefer the default workspace output location, and treat downloaded files as untrusted images because the script does not validate URL redirects, file type, or download size.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/generate.py:132
Finding

Unvalidated Remote Image URL Enables SSRF and Resource Exhaustion

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tainted flow: 'headers' from os.environ.get (line 67, credential/environment) → requests.post (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/generate.py (reported line 92)May include surrounding context.

python
sys.stdout.flush()
        
        try:
            response = requests.post(API_BASE_URL, headers=headers, json=payload, timeout=60)
            
            if response.status_code == 200:
                result = response.json()

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill documents use of environment variables and an external API, which implies access to secrets and network egress, but it does not declare any explicit tool scope such as permissions or allowed-tools. That makes the capability boundary unclear to users and hosts, increasing the risk of over-privileged execution or unexpected secret/network access when the skill is invoked.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends user prompts to a third-party image generation service and may return remote image URLs, but the description does not clearly warn users that their input leaves the local environment. This can lead to unintended disclosure of sensitive prompts, metadata exposure through remote URLs, and privacy/compliance issues if users assume the skill is local-only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module docstring and user-facing descriptions in this file are presented only in Chinese, which can force a specific language on users without opt-in. The policy allows locale constraints when they are explicitly justified, but no such justification or language choice is provided here.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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/generate.py (reported line 92)May include surrounding context.

python
sys.stdout.flush()
        
        try:
            response = requests.post(API_BASE_URL, headers=headers, json=payload, timeout=60)
            
            if response.status_code == 200:
                result = response.json()

Tainted flow: 'save_path' from os.environ.get (line 202, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
87% confidence
Finding

The output path is derived from environment variables and then written with open() without constraining it to a trusted base directory. If an attacker can influence OUTPUT_DIR_ENV or OPENCLAW_WORKSPACE, they may cause files to be written to unintended locations, potentially overwriting user-accessible files or placing content in sensitive directories.

Content

Scanner excerpt · scripts/generate.py (reported line 148)May include surrounding context.

python
try:
        response = requests.get(url, timeout=60)
        if response.status_code == 200:
            with open(save_path, "wb") as f:
                f.write(response.content)
            return True
        else:

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The activation/example language is presented only in Chinese, including the usage phrase '生图:一只可爱的小猫', which can imply a fixed language requirement for invoking the skill. The file does not state that other languages are accepted or explain why a Chinese-only interface is required.

Content

No source excerpt is available for this finding.