ClawHub
Back to skill

Security audit

Ai Provider Bridge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AI provider bridge, with expected outbound API calls when the user configures cloud providers.

Install only if you intend to send prompts and conversation context to the selected AI provider. Use Ollama for local-only operation, avoid putting secrets or regulated data in prompts unless approved, and configure only the API keys for providers you actually use.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README states that the software processes and stores data locally and does not transmit data externally unless explicitly configured by the user, but the skill’s documented purpose is to call external cloud AI providers such as Anthropic, OpenAI, Google, xAI, and Mistral. This contradiction can mislead users about where prompts and sensitive data go, causing accidental disclosure of confidential information to third-party services.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises a unified interface to multiple cloud AI providers but does not prominently warn, near the usage/description, that prompts and attached data sent to Anthropic, OpenAI, Google, xAI, or Mistral will leave the local environment and be transmitted to third-party services. This omission can cause users to unknowingly send sensitive workspace content, secrets, or regulated data to external APIs, especially because the skill presents provider switching as a simple config change.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill sends user messages and conversation history to Anthropic, OpenAI, Google, xAI, and Mistral via network requests, which can affect user privacy. In this file there is no confirmation prompt, logging, or comment/docstring warning users that their prompts and history may be transmitted to third-party services.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · README.md (reported line 56)May include surrounding context.

md
**USE AT YOUR OWN RISK.**

- The author(s) are NOT liable for any damages, losses, or consequences arising from 
  the use or misuse of this software — including but not limited to financial loss, 
  data loss, security breaches, business interruption, or any indirect/consequential damages.
- This software does NOT constitute financial, legal, trading, or professional advice.
- Users are solely responsible for evaluating whether this software is suitable for

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md
**USE AT YOUR OWN RISK.**

- The author(s) are NOT liable for any damages, losses, or consequences arising from 
  the use or misuse of this software — including but not limited to financial loss, 
  data loss, security breaches, business interruption, or any indirect/consequential damages.
- This software does NOT constitute financial, legal, trading, or professional advice.
- Users are solely responsible for evaluating whether this software is suitable for

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The code accesses provider API keys from configuration for Anthropic, OpenAI, Google, xAI, and Mistral, but this file does not include a user-facing notice or explanatory comment about handling credentials. Although expected for an AI bridge, the absence of any disclosure means users are not explicitly warned that credentials are required and used for outbound requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.