ClawHub
Back to skill

Security audit

product-video-hooks

Security checks for vulnerabilities and agentic risk

Overview

The scanners report an unpinned installation command and a gap in disclosure about sending assets to external AI services, which together support the suspicious review verdict.

Before installing, consider whether you trust the changing package invoked by the unpinned command. If you use the optional generation workflow, check what assets it sends to external services and their data-handling terms, and avoid uploading sensitive material until you are comfortable with that disclosure. The scan was partial: two referenced paths were unresolved, so the evidence is incomplete.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The documented installation command invokes an unpinned npm CLI through npx, allowing the code executed during installation to change without changes to this README. A compromised upstream release could execute with the installing user's privileges and access local files or credentials; this is a supply-chain exposure, although the finding incorrectly describes the CLI as an MCP server.

Content

No source excerpt is available for this finding.

The clip-generation workflow lacks a warning that user-provided assets are sent to third-party AI services.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The optional generation workflow passes real product imagery and character references to external AI services without explicitly explaining that these assets leave the user's environment. Naming the services and requiring approval for estimated charges provide some transparency, but do not establish informed consent to disclose confidential campaign material or identifiable imagery.

Content

No source excerpt is available for this finding.