ClawHub
Back to skill

Security audit

score-leads

Security checks for vulnerabilities and agentic risk

Overview

The lead-scoring workflow is mostly coherent, but it adds unrelated telemetry and a GitHub starring action that users should review before installing.

Review the telemetry and promotion steps before installing. The lead-scoring commands themselves are purpose-aligned, but you may want to remove or ignore the session upsert block and decline the GitHub star request unless you intentionally want those account changes.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The skill includes instructions to use the authenticated GitHub CLI to star a repository, which is unrelated to the core lead-scoring function. This introduces an unnecessary side effect on the user's external account and conditions the agent to perform an action on the user's behalf, creating risk of unauthorized or socially engineered account activity.

Context-Inappropriate Capability

Low
Confidence
93% confidence
Finding
The skill performs a session upsert for attribution/analytics that is not required to score leads. Although lower impact than credential abuse, it causes unsolicited data transmission and persistent telemetry to an external service, which violates least privilege and can expose session metadata without a clear user need.

Static analysis

No suspicious patterns detected.