Back to skill

Security audit

Pans Poc Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local POC tracking helper that stores user-entered sales POC records in a disclosed JSON file and shows no network, exfiltration, privilege escalation, or hidden behavior.

Install only if you are comfortable keeping POC/customer details in a local plaintext JSON file. Avoid entering regulated secrets or highly confidential customer data unless your local machine and backups are appropriately protected.

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
  • 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 (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises CLI operations that create, update, and store data in a local JSON file, but it declares no explicit tool scope or permissions. This creates an authorization ambiguity where an agent may be induced to perform file reads/writes without clear least-privilege boundaries, increasing the chance of unintended filesystem access or unsafe execution behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases include broad terms like “测试管理”, “技术验证”, and “proof of concept,” which are generic enough to match many unrelated user requests. Overbroad activation can cause the wrong skill to run in contexts involving customer data, operational tracking, or local file modifications, leading to unintended actions or data exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script persists customer names, owners, blockers, and customer feedback to a predictable file under the user's home directory without any notice, consent flow, retention controls, or access-hardening. In the context of a sales POC tracker, this data can contain sensitive commercial information and potentially personal data, so silent local persistence increases the risk of unintended disclosure from shared machines, backups, or other local processes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language content, including the description, headings, field explanations, and CLI guidance, is written in Chinese while the skill does not state that users may choose another language. This can violate a language/locale policy when a specific language is imposed without opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The docstring, prompts, status messages, and CLI help are written in Chinese, which effectively forces a specific language for all users. Under the stated policy, locale-specific behavior should either be optional or explicitly justified as region-specific.

Content

No source excerpt is available for this finding.