Back to skill

Security audit

Prompt Alchemist-提示词炼金术

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-optimization skill with broad activation language, but it contains only Markdown instructions and no code, persistence, credential handling, or external data flow.

Install this if you want pasted or requested prompts to be rewritten into structured optimized prompts. Be aware that its activation wording is broad, so avoid pasting sensitive text unless you actually want the agent to process it through this prompt-optimization workflow.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill auto-activates when a user merely pastes prompt text, without requiring an explicit opt-in or a tighter intent check. This can cause the skill to intercept unrelated pasted content, leading to unintended prompt transformation, context hijacking, or accidental handling of sensitive text that the user did not mean to route through this workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger description is ambiguous and lacks boundaries, so the platform may invoke the skill for loosely related requests about prompts or writing quality. While not directly harmful on its own, ambiguous routing increases the chance of unintended activation and can interfere with user intent or expose more user content to the skill than necessary.

Content

No source excerpt is available for this finding.