Back to skill

Security audit

Before/After & Transformation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a content-creation guide for honest before/after posts and does not contain hidden execution, persistence, credential use, or deceptive behavior.

Before installing, understand that this skill helps prepare public marketing content, so users should still verify consent, typical-results substantiation, legal/YMYL disclosures, and final human review before anything is published.

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
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.

Content

Scanner excerpt · references/transformation-types-and-templates.md (reported line 40)May include surrounding context.

md
## Never
Stage/exaggerate the before · use different lighting/posing for after · imply an unrealistic timeline · hide
filters/meds/surgery/pro help · cherry-pick or show only survivors · say only "results not typical" for an
outlier · use stock/other people's before-afters as clients · fabricate an average · post a client without
consent · claim WoopSocial generates the media.