Back to skill

Security audit

weekly-topic-library-generator

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill performs a disclosed weekly public-web trend research workflow and writes local Markdown/JSON outputs without hidden code, credentials, persistence, or destructive behavior.

Before installing, understand that the skill will use your agent's web-search capability and create two local output files for the week. Use it for AI short-video topic research, and review generated prompts for copyright, likeness, brand, and platform AI-label compliance before publishing.

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
91% confidence
Finding

The README instructs users to invoke the skill with "generate this week's topic library," but it does not define whether this is the only trigger phrase, what context it applies in, or any exclusion conditions. Because this is a natural-language activation description in a markdown file, the lack of specificity could cause unintended invocation or confusion about when the skill should activate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description includes broad activation phrases such as 'weekly content production' and 'viral teardown plus prompts' that could match user requests outside this skill's narrow topic-library function. In an agentic environment, over-broad triggers can cause the wrong skill to activate, leading to unintended web collection, file generation, or policy-relevant content processing without clear user intent.

Content

No source excerpt is available for this finding.