ClawHub
Back to skill

Security audit

Pixmind Video to Prompt

Security checks for vulnerabilities and agentic risk

Overview

The skill does the advertised video storyboard work, but it automatically downloads and runs cached native tooling, which deserves user review before installation.

Install only if you are comfortable with Pixmind receiving the chosen video or URL and with the skill caching and executing downloaded Node.js or FFmpeg binaries when local tools are missing. To reduce risk, preinstall Node.js and FFmpeg from trusted sources or set explicit local paths before using it, and confirm the Pixmind credit charge before each new submission.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill clearly instructs the host to use environment secrets, make network requests, and execute shell/PowerShell scripts, yet it does not declare corresponding permissions. That mismatch reduces transparency and can cause users or policy layers to underestimate the skill's capabilities, especially because it also performs downloads and launches local tooling.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The script can automatically fetch an FFmpeg binary from a remote manifest/CDN and then execute it locally. Even though it performs optional size and SHA-256 checks from the manifest, the trust root is still remote and controlled by the same distribution channel, so a compromised manifest/CDN/API base or misconfiguration could lead to execution of attacker-supplied code on the user's machine. In the context of a video-processing skill, executing newly downloaded native binaries is materially more dangerous than ordinary API usage or local file parsing.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script silently creates a cache directory and downloads a portable Node.js runtime from the network, then executes it without any explicit user notification or consent. Although it performs hash and version validation, the behavior still expands the skill's execution boundary from local-only script execution to network retrieval and binary installation, which is a meaningful supply-chain and transparency risk in an agent skill context.

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/video-to-prompt.js:326

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/video-to-prompt.js:13