ClawHub
Back to skill

Security audit

SocialKit YouTube Metadata

Security checks for vulnerabilities and agentic risk

Overview

The skill prepares and validates local YouTube metadata with proportionate access and clear user choices.

Review the generated metadata, especially the language, category and made-for-kids setting. Google credentials are unnecessary for this local drafting workflow. Review socialkit-social-core separately because it is required but was not included in the inspected bundle.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (4)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
7. Validate: `node scripts/metadata-check.mjs --dir <project-folder>`. Fix every error

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The metadata template hard-codes English as the video's default language without user choice.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to write metadata.json with defaultLanguage set to "en", without asking the user to select or confirm the language. This imposes an English locale regardless of the video's actual language, and no English-only scope or justification is documented.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
## Failure handling

- Check fails: fix the reported fields and re-run. Do not shorten text in a way that
  changes its meaning without asking.
- No thumbnail yet: leave `thumbnail` out and tell the user YouTube will pick a frame.