ClawHub
Back to skill

Security audit

Google Video Search — FlashData

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed FlashData-backed Google Videos search skill that uses an API key and paid queries, with no hidden persistence or unrelated behavior found.

Install only if you are comfortable sending your video-search queries and locale settings to FlashData and its providers, and use a protected FlashData API key with the needed scope. Watch paid-credit usage, do not paste keys into chat or files, and remember the runtime package is fetched from npm even though the examples pin its version.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The skill instructs the user to send an X-API-Key to a third-party hosted MCP endpoint and elsewhere states that queries and metadata are transmitted to FlashData and upstream providers. This is expected for a cloud API integration, but it still creates a real external-transmission risk because secrets and user query data leave the local environment and depend on correct protected-secret handling and trust in the provider.

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

md
## Connection and responses

For hosted MCP, connect `https://data.flashdata.dev/mcp` using Streamable HTTP and an `X-API-Key` header in your client's protected settings. Keep keys out of chat and committed files.

The CLI returns `{"ok":true,"tool":"google_videos","result":...}`; read the data inside `result`. MCP clients expose the same data in the tool response. Check errors before processing results. For a free quote, call `get_pricing` with `{"source":"google_videos","request_count":1}`; a quote does not run the data query.

Static analysis

No suspicious patterns detected.