ClawHub
Back to skill

Security audit

claude-autonomous-e2e

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign: scanners found one privacy-related concern about sending goal and catalog information to Open-Connect, while the scanned content showed no other reported security issues; coverage was partial.

Before installing, consider whether your goals or local catalog could contain confidential information that you do not want sent to Open-Connect. The scan covered the listed component but was marked partial because several referenced paths were missing, so the evidence does not establish that those references were inspected.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends goal and catalog information to Open-Connect without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to call Open-Connect's auto_discover with the concrete goal, which can contain user or project information. Lines 90–91 additionally require uploading the regenerated local catalog to Open-Connect, but the skill does not warn users that these details leave the local environment; its prohibition on uploading secret values does not address other confidential information.

Content

No source excerpt is available for this finding.