Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Accounts Payable Agent
v1.0.0Expert AI agent specializing in accounts payable agent. From The Agency (github.com/msitarzewski/agency-agents).
⭐ 0· 17·0 current·0 all-time
by@zhouqkt
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's stated purpose is to execute payments across ACH, wire, crypto, stablecoin, and payment APIs. However, the bundle declares no required environment variables, no credentials, and no integration points. A genuine payment-capable agent would normally require API keys, wallet credentials, bank connectivity, or at least declarations of the external tool(s) it expects to call.
Instruction Scope
SKILL.md and AGENTS.md contain detailed runtime pseudocode that calls functions like payments.send, payments.checkByReference, getScheduledPayments, lookupVendor, payments.getHistory. Those instructions presume existing platform/tooling that provides those functions, but the skill does not specify or bind to any such tooling, credentials, or endpoints. The instructions do not ask for unrelated system files or secrets beyond the missing payment integrations.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute. That minimizes on-disk risk; nothing is downloaded or installed by the skill itself.
Credentials
Given the payment capabilities described, the absence of any declared environment variables, keys, or config paths is disproportionate. Real payment operations require sensitive credentials (bank/PSP API keys, wallet private keys, webhook endpoints) but none are requested or documented here.
Persistence & Privilege
The skill is not marked always:true and is user-invocable; it does not request permanent platform privileges or claim to modify other skills. Allowing autonomous invocation (default) is normal but increases blast radius if the skill were later wired to credentials.
What to consider before installing
This skill's text shows how an Accounts Payable agent would behave, but it does not say how it would actually send money. Before installing or enabling it: 1) Ask the publisher which concrete payment integrations or platform tools implement payments.send and similar calls; require explicit documentation of where API keys or wallet credentials are stored and who controls them. 2) Do not grant any payment credentials (bank APIs, Stripe, wallet private keys, exchange keys) to this skill until you confirm an explicit, auditable integration and approval workflow. 3) Test in a sandbox environment with no funds and with strict logging and human approval gates for any payment action. 4) Verify escalation and human-approval thresholds are enforced by your platform (not just by agent instructions). 5) If you cannot confirm the skill is wired only to your organization's controlled payment backend, treat it as untrusted and avoid providing it access to credentials or live payment rails.Like a lobster shell, security has layers — review code before you run it.
agencyvk97ckkazy907knm7wrbz89a1ed84jj77ai-agentsvk97ckkazy907knm7wrbz89a1ed84jj77latestvk97ckkazy907knm7wrbz89a1ed84jj77
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🤖 Clawdis