Security audit

ghostwriter

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed interview-based writing workflow with no material security concern found.

Expect questions before a draft and wording assembled from your answers. Clarify permitted sources if you approve context research, and use placeholders for secrets. The reported scanner gap was resolved by inspecting the complete artifact; no material unresolved gap remains.

A.I.G

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

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 (1)

The activation condition covers nearly any audience-facing writing request, without requiring an interview-based workflow.

Medium

Category: Trigger Abuse
Confidence: 90% confidence
Finding: “Use when the user needs to write something for an audience” encompasses ordinary requests to draft emails, articles, or speeches. This could activate the skill when the user expects direct drafting, even though the skill requires interviewing them and forbids composing sentences they did not supply.
Content: No source excerpt is available for this finding.