费用与预算管控专家

• Outcome: Review
• Latest audit: Sep 23, 2026 · 8:30 AM UTC
• Version: 1.0.10

Overview

The skill appears to run locally without network exfiltration, but it under-discloses a persistent local trial counter and subscription gate.

Review this before installing if you expect an unlimited free local tool. It appears to keep user-provided financial table text local, but running checks writes a small counter in your home directory and enforces a 5-use trial with a subscription prompt. Treat outputs as table-based checks, not audit or compliance assurance.

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

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (76)

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

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

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The skill metadata and documentation make strong claims about automatically triaging pasted tables across 8 sub-skills, providing reproducible line-level conclusions, and naming missing columns when inputs are insufficient. The repeated static findings indicate the implemented behavior is materially narrower or different, which is a real trust and integrity issue: users may rely on the skill for controls it does not actually perform, causing missed financial, compliance, or audit issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.