Seller Profit Calculator

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 6:48 AM UTC
• Version: 1.0.2

Overview

This skill is a local Excel order-profit calculator with some broad claims and privacy documentation gaps, but its inspected behavior matches its stated purpose and shows no hidden network, persistence, or destructive actions.

Install only if you are comfortable processing order exports with this local skill. Redact unnecessary customer or business-sensitive columns before uploading files to an agent, verify output paths before using --json or --markdown, and treat the 'any platform' claim as limited to Excel order exports that contain recognizable order, revenue, cost, and profit fields. The advertised hosted API/API key option is not implemented in the inspected script, so do not rely on that README command without further verification.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (12)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The declared description promises an order profit calculator with reporting by order, store, SKU, and platform. The supplied code does not compute profit, aggregate orders, or generate reports. Instead, it analyzes spreadsheet headers and sample rows to support field mapping, with a dictionary of standard columns related to order and financial data. This looks like a preprocessing/helper component for import normalization, not the claimed end-user profit calculator itself. No concerning extra permissions or unrelated external access are present, but the primary purpose is materially different from the declared purpose.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

This markdown file describes the skill as applicable to virtually any e-commerce platform or ERP export, which is an extremely broad activation scope. It does not provide constraints, exclusions, or negative examples that clarify when the skill should not be invoked, increasing the risk of unintended use on unsupported or malformed inputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 87% confidence

Finding

The README instructs users to process order export files and configure an API key for hosted features without disclosing how sensitive order data and credentials are handled. In a tool dealing with commercial order exports, this omission can lead users to transmit business data or store secrets unsafely, increasing risk of data leakage or credential exposure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 85% confidence

Finding

This language suggests the skill can handle any platform without limitation, but provides no boundaries for when automatic field mapping will or will not work. In a markdown description, such unconstrained phrasing can act as a vague trigger by encouraging invocation in many everyday or unsupported contexts.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence

Finding

The skill advertises file-processing behavior and references scripts that can emit JSON files, but it declares no explicit tool scope or permissions boundaries. In an agent setting, missing scope constraints can cause the runtime to grant broader file-write capability than users expect, increasing the chance of overwriting local files or writing sensitive extracted data to disk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 85% confidence

Finding

The phrase 'Upload order exports from any e-commerce platform or ERP' is very broad and reads like an activation/use trigger without boundaries. The document does not provide negative examples or clear constraints on when the skill should not be used, which could cause unintended invocation for loosely related spreadsheet tasks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill explicitly instructs the agent to inspect headers and sample rows from uploaded order exports, which commonly contain sensitive commercial and personal data such as names, addresses, order IDs, phone numbers, and financial amounts. Without a clear warning, minimization guidance, or consent language, users may expose regulated or confidential data to the agent unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 81% confidence

Finding

The statement says that as long as the export contains certain standard fields, calculation will work, but it does not clearly define edge cases, exclusions, or failure conditions. This kind of broad wording can function as an ambiguous trigger for processing files that may not actually be appropriate inputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The script hard-codes Chinese header names throughout the field-mapping dictionary, and header detection also depends on Chinese labels. This creates a locale-specific behavior without offering users a language or locale choice, which matches the policy concern for forced language/locale constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

The natural-language instructions and user-facing content appear to require Chinese comprehension, but there is no opt-in, alternative locale, or explicit justification for a Chinese-only experience. Under the language policy, forcing a specific language without user choice can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

The documentation includes Chinese-only instructional text and elsewhere shows Chinese report output, but does not tell users that the skill operates in Chinese or provide an option to choose language. This may violate language/locale policy expectations when users are not explicitly opting into that locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 76% confidence

Finding

The sample report output is Chinese-only, which suggests the skill may force a specific language for generated results. The file does not mention any language preference setting, opt-in, or justification for this locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.