ClawHub
Back to skill

Security audit

openclaw-siliconflow-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed configuration guide for using SiliconFlow as an OpenClaw memory embedding provider, with the main risk being that indexed text is sent to that external embedding API.

Install only if you intend to use SiliconFlow for OpenClaw memory embeddings. Configure your own API key, index only curated files you are comfortable sending to SiliconFlow for embedding, and avoid adding private journals, inboxes, secrets, or broad repositories unless you explicitly want that content searchable.

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
  • 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
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 · SKILL.md (reported line 51)May include surrounding context.

md
model: "BAAI/bge-m3",
      fallback: "none",
      remote: {
        baseUrl: "https://api.siliconflow.cn/v1/",
        apiKey: "YOUR_SILICONFLOW_API_KEY"
      }
    }

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 · SKILL.md (reported line 150)May include surrounding context.

md
model: "BAAI/bge-m3",
      fallback: "none",
      remote: {
        baseUrl: "https://api.siliconflow.cn/v1/",
        apiKey: "YOUR_SILICONFLOW_API_KEY"
      }
    }

Static analysis

No suspicious patterns detected.