ClawHub
Back to skill

Security audit

Anthropic Connector Submit

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable checklist-style skill for preparing an Anthropic connector directory submission, with no hidden code, persistence, or data access.

Before using this skill, confirm that your MCP server actually satisfies the compliance, privacy, testing, and ownership statements it recommends selecting, and share test credentials only through a secure channel you control.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly tells users to begin with a fixed prompt, 'Respond in English. Format with clear headings and tables.' This overrides user language and formatting preferences without opt-in, which can steer interaction behavior in ways the user did not request and is a form of prompt shaping. In this context it is not highly dangerous, but it is still an unnecessary instruction that reduces user autonomy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.