ClawHub
Back to skill

Security audit

Browse website - Crawls sites automatically and mounts pages as markdown files you can grep, diff, cat, and explore with standard Unix commands — over SSH or HTTP

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate website-browsing purpose, but it tells agents to run broadly networked shell commands built from unvalidated user-controlled values.

Install only if you are comfortable sending target website domains, search terms, and requested remote commands to OpenObj. Avoid using this skill on attacker-supplied domains or terms unless the agent validates and escapes inputs, and prefer destination-scoped network access over full_network where available.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:27
Finding

Shell Command Injection Through Unsafe Template Interpolation

Content
View full analysis
Remediation
View remediation

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
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md
All commands in this skill require network access to `openobj.com`.

Use `required_permissions: ["full_network"]` for all SSH and curl commands (they need to reach openobj.com).

## How to Use

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

bash
# required_permissions: ["full_network"]
# List all pages
curl -s -X POST https://openobj.com/exec \
  -H 'Content-Type: application/json' \
  -d '{"site": "docs.stripe.com", "command": "find /site -type f"}'

Static analysis

No suspicious patterns detected.