Back to skill

Security audit

UGC & Influencer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketing workflow guide that stays within advising, drafting, planning, and rights-cleared brand posting boundaries.

Installers should treat this as a campaign-planning and drafting skill. Before publishing UGC or influencer content, users still need to confirm rights, disclosure, creator authorization, and any legal or platform-specific requirements outside the skill.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
followers.**
- **Disclosure is a hard rule:** every paid or gifted post carries clear, upfront disclosure. Asked to skip
  or bury the #ad → **decline and correct.** **Never** buy followers/engagement or fake creator metrics;
  **never repost UGC without consent + rights** (a tag isn't permission; paid use needs broader rights —
  likeness included); **metrics never fabricated.** (Full scope: `references/scope-and-connections.md`.)

## Distinct from its siblings (route correctly)
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.