Back to skill

Security audit

Business Opportunity Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown business-ideation workflow with no hidden code, persistence, credential access, or destructive behavior.

Before installing, be aware that the skill may activate for broad business brainstorming or market-research requests. Review generated search queries for your target language and locale before running them, especially the X queries that include lang:en.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The query template explicitly forces lang:en, which imposes a specific language/locale choice in the skill content. The file does not offer an alternative language option or explain why English-only filtering is required, so this is a natural-language locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This template again uses lang:en, forcing English-language content for the search. Because the document does not provide opt-in, alternatives, or a documented justification for restricting results to English, it violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The lang:en filter appears here as well, making the locale constraint systematic rather than incidental. The file does not state that this is a region-specific or English-only research tool, so the forced language setting is a policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The invocation description is excessively broad and overlaps with many common user requests, including general market research, brainstorming, pain points, and 'what should I build' questions. In agent systems that auto-select skills from descriptions, this can lead to unintended routing, causing this skill to capture prompts meant for other domains and potentially initiate unnecessary research, content generation, or follow-on phases.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger at this location includes very broad conditions such as users wanting to explore a market or asking for random ideas, which can match many ordinary brainstorming requests. This can cause the skill to activate when the user did not intend business ideation specifically, steering the conversation into a predefined workflow and increasing the chance of irrelevant or over-privileged tool usage in environments where skills can invoke web search or artifact generation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

Line L85 includes a locale-specific instruction for the 'Indonesian Market' with an example phrase in Indonesian. Because the guide provides a language/locale directive without stating that this should be chosen based on user preference or explicit market targeting input, it can encourage forced locale output contrary to language-choice policy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.