abra-flexibee
ABRA FlexiBee integration. Manage data, records, and automate workflows. Use when the user wants to interact with ABRA FlexiBee data.
58
67%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./skills/abra-flexibee/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
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
The skill is an explicit integration with ABRA FlexiBee — an accounting/ERP system — and exposes domain-specific financial objects (Invoice, Payment, Product, Company). It provides Membrane actions and a proxy that allow the agent to run actions and send arbitrary HTTP methods (POST/PUT/PATCH/DELETE) to the ABRA FlexiBee API (e.g., creating/updating/deleting invoices or payment records). This is not a generic browser or generic HTTP tool: it is a purpose-built connector for a financial/accounting system and therefore enables direct financial operation (recording/creating payments and invoices) via API calls.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
The skill runs the Membrane CLI against the external app URL "https://www.flexibee.eu/" (via membrane connection ensure ...) and the remote connection object can include clientAction.agentInstructions returned at runtime that directly instruct the AI agent, while the skill relies on Membrane/remote content as a required dependency.
- Repository
- membranedev/application-skills
- Commit
f484c82
- 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.