Security audit

DrawThings Image Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently wraps a local DrawThings image-generation API, with manageable privacy and supply-chain cautions but no evidence of hidden or malicious behavior.

Install only if you are comfortable sending prompts to the configured DrawThings endpoint. Keep DRAWTHINGS_URL on localhost unless you intentionally trust a remote server, avoid putting secrets or private data in prompts, strip metadata before sharing generated files when privacy matters, and prefer verified .safetensors models over untrusted checkpoint files.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (3)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/generate.py:57
Finding: Unrestricted API Destination Can Expose Prompts and Reach Internal Services
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: scripts/generate.py:17
Finding: Unpinned Runtime Dependency Installation Guidance
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: references/models.md:47
Finding: Documentation Recommends Unverified Community Models and Unsafe Checkpoint Format
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill advertises use of environment variables, file output, and network access but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an authorization ambiguity: an agent/runtime may grant broader capabilities than users expect, making network requests and file writes possible without clear least-privilege boundaries.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill states that PNG outputs embed prompt and generation metadata, but it does not clearly warn users that this can expose sensitive prompt contents, seeds, timestamps, or workflow details when images are shared. In this context, prompts may contain proprietary concepts, personal data, or internal instructions, so silent metadata retention creates a realistic confidentiality risk.
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 77)May include surrounding context.
python
} try: response = requests.post(endpoint, json=payload, timeout=300) response.raise_for_status() return response.json() except requests.exceptions.ConnectionError:

Static analysis

No suspicious patterns detected.