ClawHub
Back to skill

Security audit

Art Deco Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple image generator that uses an external API; the main risk is that prompts, reference IDs, and the API token are sent to that service.

Install only if you are comfortable sending art prompts, optional reference image IDs, and a Neta/TalesOfAI API token to api.talesofai.com. Avoid confidential prompts or sensitive internal asset IDs, and prefer a low-privilege or temporary token because the documented CLI flag can expose secrets in shell history or process metadata.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill declares only `Bash` in metadata but its documented behavior depends on calling the external Neta API, which implies network access without an explicit permission declaration. This weakens transparency and policy enforcement because users and reviewers may not realize the skill can transmit prompts and tokens to a third-party service.

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill metadata and user-facing messaging claim it uses the Neta AI API, but the code actually transmits prompts and credentials to TalesOfAI endpoints. This is dangerous because users may disclose prompts, references, and API tokens under false assumptions about the receiving service, defeating informed consent and potentially routing data to an unintended third party.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README instructs users to send prompts, tokens, and optional reference-image identifiers to a third-party image-generation API but does not clearly disclose that user-supplied content is transmitted off-platform. This can lead users to submit sensitive text prompts or internal asset identifiers without informed consent, creating privacy, confidentiality, and data-governance risk.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script requires an API token via a command-line flag, which can expose the secret through shell history, process listings, job logs, or agent telemetry. In an agent/automation context this is more dangerous because credentials are often captured by orchestration systems and can be recovered by other local users or administrators.

Static analysis

No suspicious patterns detected.