Back to skill

Security audit

Prompt Library Curator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static prompt-library helper with a clearly disclosed English/Spanish scope and no executable or privileged behavior.

Installers should understand this skill only provides bundled prompt templates in English and Spanish. It appears low risk from a security standpoint, but users should still review generated finance, HR, or business prompts before relying on them for professional decisions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The CSV enumerates prompts only for 'en' and 'es', and each prompt text is hardcoded in that language. This can constitute a locale/language policy violation because the skill content is constrained to specific languages without indicating user choice, opt-in, or a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description and capability list state that the skill supports only EN/ES, which is a natural-language locale constraint. The file does not justify the restriction as region-specific or explicitly frame it as an opt-in choice beyond asking users to pick between those two languages.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.