ClawHub
Back to skill

Security audit

YouTube Autocomplete — FlashData

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed FlashData integration for YouTube autocomplete queries, with expected external API use and no hidden or destructive behavior found.

Install only if you are comfortable sending YouTube query text and locale settings to FlashData and using paid FlashData Credits. Store FLASHDATA_API_KEY only in protected secret configuration, scope it to the needed source, and review the pinned npm package/version before use in stricter environments.

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 (3)

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
84% confidence
Finding

The skill explicitly instructs the agent/client to send user queries and an API key to external FlashData endpoints, which creates real data exfiltration risk to a third party. While this is the intended function of the integration and not inherently malicious, it is still a genuine security/privacy boundary crossing because sensitive prompts, locale data, and billing-linked credentials leave the local environment.

Content

Scanner excerpt · SKILL.md (reported line 87)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":"youtube_suggestions","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":"youtube_suggestions","request_count":1}`; a quote does not run the data query.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The schema sets a default language of "en", which creates an implicit language choice when the user does not specify one. Per the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.