Back to skill

Security audit

Product Scoper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only product scoping guide with no code execution, persistence, credential access, or hidden data handling.

Installers should expect this skill to guide MVP scoping decisions. Review the language and platform defaults before applying them, especially if the product is not China-focused or needs multilingual launch support.

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
93% confidence
Finding

The skill description includes broad trigger phrases like 'what to build first' and general MVP/product-scoping terms, which can overlap with ordinary planning conversations and cause unintended invocation. Over-broad activation increases the chance the agent routes users into this skill when they did not ask for structured scoping, potentially bypassing a more appropriate or safer skill and degrading reliability of system behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L16 states "Chinese only for MVP" and defers English until later, which imposes a language choice rather than offering user selection or opt-in. This matches the policy category for language or locale constraints that are not explicitly optional or justified as region-specific.

Content

No source excerpt is available for this finding.