Back to skill

Security audit

Pans Roi Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow AI compute ROI calculator with no network, credential access, hidden persistence, or unsafe execution behavior found.

Install only if you want a Chinese-language ROI/TCO helper for AI compute or GPU sales analysis. Be aware that broad ROI trigger phrases may activate it for general finance questions, so users should keep inputs scoped to AI infrastructure comparisons.

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
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
90% confidence
Finding

The trigger phrase '投资回报' is highly generic and can overlap with many unrelated finance or strategy requests. This ambiguity increases the chance of accidental invocation, which can expose user data to the wrong skill context and produce misleading outputs under an AI infrastructure ROI framing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger phrase '投资回报' is highly generic and can overlap with many unrelated finance or strategy requests. This ambiguity increases the chance of accidental invocation, which can expose user data to the wrong skill context and produce misleading outputs under an AI infrastructure ROI framing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file description and user-facing text are entirely in Chinese, indicating the skill is designed to operate in a fixed language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

A trigger section without exclusions or negative examples leaves invocation boundaries unclear, especially when several listed phrases are already broad. This raises the risk of misrouting benign business conversations into this skill, which can degrade reliability and increase inappropriate processing of sensitive pricing or commercial data.

Content

No source excerpt is available for this finding.