ClawHub
Back to skill

Security audit

NewsRiver Global Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent YieldCircle API guide, but it exposes live crypto trading, bridging, wallet creation, and email/SMS actions without enough built-in user-control guidance.

Install only if you intend to use YieldCircle for crypto intelligence and possible transaction execution. Before allowing an agent to use it, require explicit approval for swaps, bridges, yield actions, wallet creation, email, SMS, and scraping; set spending and slippage limits; verify receiver addresses; and avoid sending secrets, wallet credentials, private keys, or unnecessary personal data to the API.

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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly promotes live DeFi swaps, cross-chain bridging, wallet creation, and outbound proxy actions without prominent safety gating, confirmation requirements, or warnings about irreversible financial and external-world consequences. In an agent context, this materially increases the chance of unintended fund movement, unsafe transaction execution, or abuse of email/SMS capabilities from natural-language prompts.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This example shows a POST to an external API that can initiate a swap workflow using agent-specific parameters, including asset pair, amount, and receiver. Even with dry_run shown in the snippet, the surrounding skill advertises live execution, so embedding direct transaction-oriented API usage in an agent skill is dangerous unless strict approval and validation controls are enforced.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

bash
# Cross-chain swap: USDC on Base → POL on Polygon (LIVE ✓)
curl -X POST https://api.yieldcircle.app/api/defi/swap \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": 2,

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This example shows a POST to an external API that can initiate a swap workflow using agent-specific parameters, including asset pair, amount, and receiver. Even with dry_run shown in the snippet, the surrounding skill advertises live execution, so embedding direct transaction-oriented API usage in an agent skill is dangerous unless strict approval and validation controls are enforced.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

bash
# Cross-chain swap: USDC on Base → POL on Polygon (LIVE ✓)
curl -X POST https://api.yieldcircle.app/api/defi/swap \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": 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 60)May include surrounding context.

bash
curl -H "X-API-Key: $NEWSRIVER_API_KEY" \
  "https://api.yieldcircle.app/api/v1/analysis/correlation?topic=ETF&symbol=BTC-USD"

4. "On This Day" Historical Memories

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

The AskRiver chat endpoint sends arbitrary natural-language messages to an external service, which creates potential for prompt/data exfiltration if an agent forwards sensitive context, secrets, or user data. In this skill, the danger is elevated because the same integration also offers actionable financial and proxy capabilities, making inadvertent leakage or cross-feature misuse more consequential.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

5. AskRiver AI Chat (PREMIUM)

Natural-language intelligence queries powered by Gemini. Searches 288K+ articles from 277 sources across 137 countries.

bash
curl -X POST "https://api.yieldcircle.app/api/v1/askriver" \
  -H "X-API-Key: $NEWSRIVER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message": "What is the latest crypto market sentiment?"}'

Static analysis

No suspicious patterns detected.