agentcash-wallet
Manage your agentcash wallet and call any x402-protected API with automatic payment. No API keys, no subscriptions — just a funded wallet (USDC on Base). USE FOR: - Checking wallet balance before API calls - Redeeming invite codes for free credits - Getting deposit address for USDC - Discovering endpoints and pricing on any x402-protected origin - Making paid API requests via the agentcash CLI - Troubleshooting payment failures TRIGGERS: - "balance", "wallet", "funds", "credits", "x402" - "redeem", "invite code", "promo code" - "deposit", "add funds", "top up" - "discover", "endpoints", "what APIs", "pricing" - "insufficient balance", "payment failed"
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
3 findings — 3 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 1.00). The skill's required workflow uses `npx agentcash discover <origin>` to fetch endpoint catalogs and their `instructions` field from arbitrary public origins (e.g., https://stableenrich.dev, https://stablesocial.dev), and explicitly tells the agent to read those third-party instructions which can influence subsequent API calls and behavior.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). Yes — the skill's runtime calls (e.g., npx agentcash discover https://stableenrich.dev) fetch an "instructions" field from that origin which the skill explicitly requires and directs the agent to read and follow, so remote content at https://stableenrich.dev can directly control prompts/instructions.
W009: Direct money access capability detected (payment gateways, crypto, banking)
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
Direct money access detected (high risk: 1.00). The skill explicitly manages an on-chain wallet and performs cryptocurrency payments. It provides wallet creation/storage, deposit addresses for USDC on the Base network, a redeem flow for credits, and commands that "sign USDC payment" and automatically settle payments when calling x402-protected APIs (npx agentcash fetch). This is a purpose-built payment tool (wallet + automated transaction signing/settling), not a generic API caller or browser automator. Therefore it grants direct financial execution capability.
- Repository
- Merit-Systems/agentcash-skills
- Commit
fe3e7ab
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.