Accounts Receivable Manager
v1.0.0Automate accounts receivable: aging reports, prioritize collections, draft payment reminders, match payments, track DSO, and forecast bad debt exposure.
⭐ 0· 552·0 current·0 all-time
by@1kalin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name, description, README, and SKILL.md are consistent: all content focuses on AR aging, prioritization, reminders, cash application, DSO and bad-debt forecasting. The skill is instruction-only and does not request unrelated binaries, environment variables, or system paths.
Instruction Scope
The runtime instructions stay within AR workflows (reports, scoring, email templates, cash-application rules). However the SKILL.md is high-level and does not specify how the agent should access invoice/payment data or what connectors to use. That vagueness could lead an agent to ask for or attempt access to financial systems or files unless the user provides explicit constraints.
Install Mechanism
No install spec and no code files — this is instruction-only, so nothing is written to disk or downloaded by the skill itself.
Credentials
The skill declares no required credentials or env vars, which is proportionate to an instruction-only template. In practice, to run on real company data you will need connectors/credentials for accounting/ERP/CRM systems; those are not declared here and must be provisioned separately with least privilege.
Persistence & Privilege
always is false and there is no install or configuration writing. The skill does not request persistent system presence or attempt to modify other skills or agent-wide settings.
Assessment
This skill appears coherent for AR tasks, but it is a high-level, instruction-only template from an unknown source. Before installing or using it: 1) do not upload real financial data until you confirm where processing happens (local vs external) and how data is stored/retained; 2) provision only the minimal connectors/credentials the agent needs, using least privilege and rotation; 3) ensure the agent cannot auto-send emails or change accounting records without an explicit, auditable human approval step; 4) test on synthetic or redacted data first; 5) verify the publisher (the homepage links in the README point to afrexai-cto.github.io) and review any paid add-ons before providing payment or credentials. If you want stronger assurance, ask the publisher for a provenance statement or a code-backed implementation that declares required connectors and data flows.Like a lobster shell, security has layers — review code before you run it.
ARvk9715bweqy1r0y9gtvgk3e9z3h8160c5accountingvk9715bweqy1r0y9gtvgk3e9z3h8160c5collectionsvk9715bweqy1r0y9gtvgk3e9z3h8160c5financevk9715bweqy1r0y9gtvgk3e9z3h8160c5invoicingvk9715bweqy1r0y9gtvgk3e9z3h8160c5latestvk9715bweqy1r0y9gtvgk3e9z3h8160c5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.