Back to skill

Security audit

Pans Upsell Radar

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent local upsell-analysis tool, but it bundles and persists real-named customer-like commercial records in plaintext without clear provenance or controls.

Review the bundled customer data before installing. If these records are real or derived from real customers, they should be removed or replaced with clearly fictional examples, and runtime data should have documented retention, deletion, and file-permission controls.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/upsell.py:47
Finding

Plaintext Customer Commercial and Operational Data Bundled with the Skill

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases include broad business terms such as 'upsell', '交叉销售', and '客户增长', which could activate the skill during ordinary conversations unrelated to intentional skill use. Overbroad activation increases the chance of unintended context capture, surprising behavior, or unsolicited business analysis based on user content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script automatically creates a local data directory under the user's home folder and writes customer and sales-signal data to JSON files without notice, consent, or any data-handling controls. Because the stored content includes identifiable customer names, spending, team size, and business activity signals, this can expose sensitive commercial information to other local users, backups, or endpoint monitoring systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

All user-facing description and usage guidance are written in Chinese, and the file does not state that other languages are supported or that Chinese is an intentional opt-in locale. Under the stated policy, forcing a specific language without user choice can be a natural-language policy concern unless clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This JSON data includes multiple natural-language string values exclusively in Chinese, such as client names at L03, L09, L15, and L21, without any indication that the skill is region-specific or that users can opt into this locale. Under the policy for natural-language issues, fixed locale-specific content can be a violation when no choice or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The docstring and user-facing CLI descriptions/output are written in Chinese, which imposes a specific language/locale without any opt-in or alternative. The policy calls for flagging language or locale constraints unless the skill offers user choice or clearly documents a justified region-specific limitation.

Content

No source excerpt is available for this finding.