Back to skill

Security audit

全域电商经营专家团

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed e-commerce reporting and validation workflow, with local report generation, evidence gates, and multi-agent coordination that fit its stated purpose.

Before installing, be comfortable with a local Python workflow that reads uploaded business reports, writes report and audit files, may use a local client-name registry for leak checks, and creates/waits on WorkBuddy team tasks. Review generated business recommendations before acting on them; the package includes approval gates and a mock connector, but real platform changes should remain under explicit human approval.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (113)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The implementation is described as a PDF layout/typesetting tool that does not perform the promised analytics or numeric-source validation. The main security issue is hidden file-generation and possible false assurance about data governance, which can lead users to trust outputs that were never actually validated as claimed.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
ROOT = Path(__file__).resolve().parents[1]
GUARD = ROOT / "scripts" / "claim_guard.py"
ENV = {**os.environ, "PYTHONUTF8": "1"}
PERIOD = "2026-W01"
SOURCE_HASH = hashlib.sha256(b"claim-guard-smoke-source").hexdigest()
Confidence
60% confidence
Finding
Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Static analysis

No suspicious patterns detected.