Back to skill

Security audit

anthropic api

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for using Anthropic Claude APIs through an MCP server, with external API use clearly aligned to its purpose.

Install only if you intend agents to send selected prompts, images, documents, or batch requests to Anthropic using your Anthropic API key. Review costs and data-sharing expectations before using it with sensitive content, and keep the API key in environment configuration rather than prompts or logs.

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
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 (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/endpoints.md (reported line 3)May include surrounding context.

md
# Reference — Endpoints / Tools

The skill operates through the **four MCP tools** of the Anthropic MCP server. Each maps to one or more Anthropic API endpoints (base `https://api.anthropic.com/v1`).

For full schemas and I/O examples, see the MCP tools reference: [../../mcp/docs/03-tools-reference.md](../../mcp/docs/03-tools-reference.md).