ClawHub
Back to skill

Security audit

AgentAPI

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for finding AgentAPI directory entries, with disclosed external lookup URLs and payment cautions but no executable behavior.

This skill is reasonable to install if you want AgentAPI directory lookup help. Treat AgentAPI queries as external network requests, avoid putting secrets in search terms, and require explicit confirmation, recipient verification, and spending limits before using any x402 payment flow outside this documentation-only skill.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
### ⚠️ Important Safety Notice

**x402 payments require explicit setup and should not be automated without safeguards:**

- **Wallet required:** You must configure a wallet with USDC on Base
- **User approval recommended:** Implement confirmation flows before any payment

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 16)May include surrounding context.

md
A curated directory of APIs designed for AI agents. Machine-readable. MCP-compatible. Agent-accessible.

**Website:** https://agentapihub.com  
**Docs:** https://api.agentapihub.com/api/docs

## Free Features

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 62)May include surrounding context.

md
A curated directory of APIs designed for AI agents. Machine-readable. MCP-compatible. Agent-accessible.

**Website:** https://agentapihub.com  
**Docs:** https://api.agentapihub.com/api/docs

## Free Features

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
- **User approval recommended:** Implement confirmation flows before any payment
- **Verify recipient:** The payment recipient is `0xcCb92A101347406ed140b18C4Ed27276844CD9D7` (gizmolab.eth)
- **Set spending limits:** Configure maximum per-request and daily limits
- **This skill does not auto-execute payments** — it provides documentation only

For implementation details, see: https://api.agentapihub.com/api/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description broadly states that the skill can browse and search the AgentAPI directory, but it does not specify when the skill should be invoked versus when other general web/API lookup skills should be used. Because this is a markdown/manifest context, the absence of narrower trigger conditions or exclusion examples can lead to unintended invocation overlap.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.