ClawHub
Back to skill

Security audit

Reelary B-roll Finder

Security checks for vulnerabilities and agentic risk

Overview

The skill searches the user’s footage for relevant clips, with a routine dependency risk in its optional command-line fallback.

Prefer an installed or reviewed, version-pinned Reelary CLI. Review the separate setup skill before indexing folders, and check linked editing skills before using their workflows.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

MCP server referenced without pinned version: 'npx -y reelary'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The fallback command uses npx -y reelary without a version pin, allowing npm to fetch and execute a changing package version without an installation confirmation. If a future release or its dependency chain is compromised, it could execute code with the user's permissions and access local footage or other files; the skill's local-processing claim does not prevent this supply-chain risk. This is a CLI dependency risk rather than evidence of an unpinned MCP server, and no malicious intent is apparent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.