Back to skill

Security audit

Prompt Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple prompt-improvement guide with no code execution, persistence, or data access, though users should adjust its language examples to their own needs.

Before using the skill, review optimized prompts for unwanted fixed-language requirements and change them to match the user's preferred language; no special security-sensitive permissions are evident from the artifact.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The markdown instructs users to add the constraint "Output in Chinese" as a generic optimization pattern, which can impose a specific language regardless of user preference. Under the language/locale policy, forcing a language without explicit opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The example ends with "Language: Chinese," which directs a specific locale in the generated output. Because the skill presents this as a standard optimized prompt example and does not mention user choice, it violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.