ClawHub
Back to skill

Security audit

Opportunity Radar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a research workflow that stays within private evidence gathering and clearly gates any external action behind exact approval.

Install only if you want an agent to perform live, evidence-led market research for a moneyprinter route. Review staged external actions carefully before approving them, especially anything involving outreach, spend, accounts, posting, or regulated claims.

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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Require `Run Authorization`, the current `Money Machine Run`, `Revenue Profile`,
and `Experiment Brief` from `moneyprinter`. Run Authorization satisfies the
route prerequisite for private research, analysis, and artifact creation. Use
it without asking for another approval. If it is missing or the route has
materially changed, return to `moneyprinter` for confirmation rather than
inventing permission. Run Authorization never permits contact, posting,
purchase, account mutation, or another external commitment.
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.

Static analysis

No suspicious patterns detected.