Back to skill

Security audit

axiom-iban-validator

Security checks for vulnerabilities and agentic risk

Overview

This is a local IBAN validation helper with some documentation mismatches, but no hidden access, persistence, credential use, network behavior, or destructive actions.

Install only if a local, offline IBAN format/checksum check is sufficient. Do not treat a valid result as proof that the bank account exists or is safe to pay, and expect some documentation examples to need correction before developer use.

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
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill metadata and documentation claim support for validating IBANs for 100+ countries, but the implementation is reported to support only a much smaller subset. In a financial-validation context, this can cause unsupported-country IBANs to be incorrectly rejected or mishandled, leading downstream systems or users to make trust decisions based on inaccurate validation coverage claims.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file presents the skill description and usage guidance entirely in Chinese, with no indication that users may choose another language or that the locale restriction is intentional and justified. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest describes the skill as checking IBAN format and mod-97 checksum for 100+ countries. However, the module docstring explicitly says '~40 pays principaux supportés' and 'not the complete ISO 13616 list', which narrows the represented coverage and creates a semantic mismatch about actual supported scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documentation is written in French throughout key user-facing sections such as problem statement, usage labels, tests, limitations, and spec. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation, and this README does not indicate that the skill is intentionally limited to French-speaking users or a French-only deployment context.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The inline documentation states that only about 40 major countries are supported, but the IBAN_LENGTHS table that follows contains a much larger set of country codes, roughly consistent with broad multi-country support. This is an active contradiction between documentation and implemented behavior, not merely an omission.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The top-level natural-language documentation is written entirely in French, including the limitations and title text, with no indication that the skill is intentionally region-specific or that users can opt into another language. This creates a locale/language policy concern because the skill presents a fixed language experience rather than offering a choice or documenting the constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.