ClawHub
Back to skill

Security audit

client-onboard

Security checks for vulnerabilities and agentic risk

Overview

This skill generates local onboarding documents for a freelance client project, with no evidence of hidden execution, credential access, exfiltration, or persistence.

Review the generated CLAUDE.md and client-facing drafts before copying or sending them, especially assumptions about stack, payment schedule, deployment, and local environment files. Installation appears reasonable for users who want an automatic local document generator for new freelance projects.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 273)May include surrounding context.

md
├── scripts/                    # One-off scripts + automation
├── docs/                       # Client-facing documentation
│   └── ADMIN_GUIDE.md
├── .env.local                  # Local env vars (not committed)
├── .env.example                # Template for env vars
├── CLAUDE.md                   # Claude Code context for this project
├── SPEC.md                     # Project specification

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad phrases like "I just got a project" and an open-ended condition of "any time a new freelance project is starting." These overlap with normal conversation and do not clearly bound when the skill should activate versus when it should not.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% 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 136)May include surrounding context.

md
- *Why*: Industry standard, great DX, handles PCI compliance

### Deployment
- **Frontend**: Vercel (auto-deploy on git push)
- **Backend**: Supabase managed (no ops)
- **[If needed] Workers**: Railway (simple, cheap, no k8s)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% 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 175)May include surrounding context.

md
- *Why*: Industry standard, great DX, handles PCI compliance

### Deployment
- **Frontend**: Vercel (auto-deploy on git push)
- **Backend**: Supabase managed (no ops)
- **[If needed] Workers**: Railway (simple, cheap, no k8s)

Static analysis

No suspicious patterns detected.