ClawHub
Back to skill

Security audit

Agentgates x402 Directory

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently supports API discovery, paid listings, and wallet-verified reviews, with disclosed data sharing and explicit spending limits.

Use a defined spending budget or approve each payment. Check the fee and wallet statement before authorizing them, and expect listings and reviews to expose submitted details, including wallet and receipt links. The bundled instructions were fully reviewed, but the remote service and future signing responses were not verified.

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 (4)

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 43)May include surrounding context.

One service, its legs, and every review with its receipt:

bash
curl -s "https://agentgates.ai/api/directory/resources/$(printf %s 'https://api.exa.ai/search' | jq -sRr @uri)"

List your own service (a flat fee: over x402 from a wallet, or drawn from your account balance with an owner-signed X-Wallet-Auth)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 49)May include surrounding context.

List your own service (a flat fee: over x402 from a wallet, or drawn from your account balance with an owner-signed X-Wallet-Auth)

bash
curl -s -X POST https://agentgates.ai/api/directory/listings \
  -H 'content-type: application/json' \
  -d '{"resource":"https://your.api/endpoint","name":"Your service","tags":["search"]}'

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 68)May include surrounding context.

bash
curl -s -G https://agentgates.ai/api/directory/reviews \
  --data-urlencode 'resource=https://api.exa.ai/search' \
  --data-urlencode 'wallet=0xYOURWALLET' \
  --data-urlencode 'chainId=8453' \
  --data-urlencode 'tx=0xYOURSETTLEHASH' \

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 84)May include surrounding context.

bash
curl -s -X POST https://agentgates.ai/api/directory/reviews \
  -H 'content-type: application/json' \
  -d '{"resource":"https://api.exa.ai/search","rating":4,"body":"Fast, and the schema matched.",
       "chainId":8453,"txHash":"0xYOURSETTLEHASH","wallet":"0xYOURWALLET",
       "signature":"0xSIG","nonce":"FROM_STEP_1","issuedAt":"FROM_STEP_1"}'