Back to skill

Security audit

tech-to-product

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only skill for turning materials or material-science technologies into productization guidance, with no executable code or privileged behavior.

Install only if you want a materials-to-product analysis template. Be aware it may activate on broader technology-productization prompts unless the routing description is narrowed, but it does not request privileged access or run code.

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
86% confidence
Finding

The activation language is broad enough to match many ordinary questions about technology, products, or applications, which can cause the wrong skill to trigger. Over-broad routing is dangerous because it can override more appropriate domain-specific or safety-constrained skills, leading to irrelevant guidance, degraded controls, or policy bypass in downstream handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The expected input section is ambiguous about routing boundaries and does not clearly distinguish this skill from general technology-application or implementation-analysis skills. This ambiguity increases the chance of accidental invocation on unrelated prompts, which can misroute requests and weaken specialized handling or safety scoping.

Content

No source excerpt is available for this finding.