Back to skill

Security audit

Listicle & Roundup

Security checks for vulnerabilities and agentic risk

Overview

This is a content-planning skill for honest listicles and roundups, with no executable code or hidden persistence.

Installers should treat rankings and product claims as draft editorial work: verify facts, contributor consent, affiliate or sponsor disclosures, and any YMYL disclaimers before publishing through WoopSocial or another channel.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill contains contradictory scope statements: it repeatedly instructs the agent to curate, rank, and order items by stated criteria, but later says the agent does not 'rank, or judge a list.' This ambiguity can cause downstream agents or orchestrators to ignore intended safety boundaries, either letting the model make unverified evaluative claims or causing humans to overtrust rankings as if they were already vetted. In a content-generation workflow focused on 'best of' lists, that inconsistency increases the chance of misleading rankings, undisclosed bias, or fabricated comparative judgments slipping into published output.

Content

No source excerpt is available for this finding.