ClawHub
Back to skill

Security audit

Film Photo Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward remote image generator, but users should understand that prompts, reference IDs, and the API token go to the Neta/TalesOfAI service.

Install only if you trust the Neta/TalesOfAI API and the skill publisher with your image prompts, reference IDs, and API token. Avoid confidential or regulated prompts, prefer a dedicated/revocable API token, and be aware that passing secrets on the command line can expose them through shell history or process listings.

SkillSpector

By NVIDIA
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 advertises use of an external Neta API token and command examples that clearly imply outbound network access, yet the manifest declares only `tools: Bash` and no explicit permission model for networking. This creates a transparency and consent problem: an agent or user may invoke the skill without realizing it sends prompts and tokens to a third-party service, increasing the risk of unintended data exfiltration or policy bypass.

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill metadata claims it uses the Neta AI API, but the implementation sends prompts and credentials to api.talesofai.com instead. This service mismatch is a real trust-boundary violation because users may provide sensitive prompts or tokens under false assumptions about the recipient, and the discrepancy is especially suspicious in a credentialed networked skill.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README clearly instructs users to send prompts, tokens, and optional reference-image identifiers to a third-party image-generation API, but it does not warn that user-supplied content leaves the local environment and is processed externally. This creates a real privacy and data-handling risk because users may submit sensitive prompts or identifying reference-image data without understanding the external disclosure.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
Accepting the API token via a command-line flag exposes the secret through shell history, process listings, logging, and job runners. In a skill that immediately transmits that token to an external API, this creates a practical credential leakage risk even if the code is otherwise functioning as intended.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.