Back to skill

Security audit

pricing-presentation

Security checks for vulnerabilities and agentic risk

Overview

The verdict is suspicious because the skill’s reported implementation falls short of its advertised pricing-presentation purpose, and the scanner also flagged an undeclared file-writing capability.

Review the skill’s actual output and intended file access before installing. The reported output does not match the advertised presentation, and the scan was partial; the suspicious verdict signals review is warranted, not that malicious intent was established.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code implements the tracked-link portion of the description, but its sole output is tracked-links.md. It does not process tier prices or presentation content, and the three fixed guardrails are instructions rather than disclosures tailored to the advertised offers. These omissions materially narrow the declared primary deliverable. The local CSV reads and output-file writes are ordinary supporting behavior; no network requests or unrelated capabilities are present.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

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.