Back to skill

Security audit

job-description-writer

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill drafts job postings and writes a local length report, with publication and hiring decisions left to the user.

Choose an output folder where replacing length-check.md is acceptable, and have HR review the draft's legal claims before publishing. The optional Windows download is unnecessary for the bundled workflow. The publisher's [release page](https://github.com/rapidworker1/Multiple-AI-models-Toolkit/releases/tag/Main) describes a separate multi-model app; this verdict does not assess that executable, and the supplied hash alone does not establish its safety.

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

SkillSpector findings are pending for this release.