ClawHub
Back to skill

Security audit

rwa-data-api

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses its paid market-data service, with no evidence of hidden access, secret collection, or unrelated behavior.

Set a spending limit and verify the payment amount, recipient, network, and USDC mint before signing. Keep private keys out of API requests, and omit confidential information from submitted claims and research topics. Live service behavior and publisher identity could not be independently 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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 81)May include surrounding context.

bash
# 1. Request without payment → 402 challenge
curl -s -D - https://rwa-data-api.dave-a-bear.workers.dev/metric/stablecoin_market_cap -o /tmp/challenge.json
# Response: HTTP 402, PAYMENT-REQUIRED header (base64 JSON with amount, asset mint, pay_to)

# 2. Decode the challenge, send the EXACT USDC amount on Solana mainnet to pay_to

The custom-brief workflow sends research topics to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to submit a research topic to the third-party API, rather than merely listing an available tool. Although payment costs are disclosed, there is no warning that user-provided topics could reveal confidential research interests or other sensitive information to the service operator.

Content

No source excerpt is available for this finding.