ClawHub
Back to skill

Security audit

Browser Fu

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for browser troubleshooting, but it needs review because it encourages reuse of live browser session cookies in direct API calls without enough safeguards.

Install only if you are comfortable with the agent using browser sessions for troubleshooting. Before following the API-discovery advice, avoid copying live cookies into shell commands, prefer unauthenticated or least-privilege tokens, confirm the exact destination origin, and require explicit approval before any authenticated or state-changing request.

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

Warning
Location
references/api-discovery.md:41
Finding

Unsafe Exposure of Browser Session Cookies Through Command-Line Requests

Content
View full analysis
Remediation
View remediation

SkillSpector

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

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · references/api-discovery.md (reported line 45)May include surrounding context.

bash
# REST example
curl -s "https://example.com/api/v1/items?page=1&limit=100" \
  -H "Cookie: session=..." | python3 -m json.tool

# Or use web_fetch

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The guidance explicitly suggests replaying authenticated API requests with browser session cookies, but it provides no warning about handling, minimizing, or protecting authentication material. In an agent skill focused on browser troubleshooting and scraping, this can normalize exfiltrating or reusing live session credentials in external tools or logs, increasing the risk of account compromise or unauthorized data access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.