ClawHub
Back to skill

Security audit

Skillforge

Security checks for vulnerabilities and agentic risk

Overview

SkillForge is a small local tool for generating SKILL.md files, with no evidence of hidden data access, persistence, or exfiltration.

Install only if you are comfortable with the listed Python dependencies and run the server locally. Review generated SKILL.md files before publishing, especially when the input instructions come from someone else.

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Content
## Generate a SKILL.md

```bash
curl -s -X POST http://localhost:8003/v1/forge-skill \
  -H "Content-Type: application/json" \
  -d '{"name": "My Cool Tool", "description": "Does cool things.", "instructions": "Step 1: Be cool."}' | jq
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
## With optional env vars and bins

```bash
curl -s -X POST http://localhost:8003/v1/forge-skill \
  -H "Content-Type: application/json" \
  -d '{"name": "API Client", "description": "Calls APIs.", "instructions": "Use curl.", "env_vars": ["API_KEY"], "bins": ["curl"]}' | jq '.skill_md' -r
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.