Security audit

content-research-writer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain writing-assistant skill whose research, citation, and draft-feedback behavior matches its stated purpose.

Before publishing, independently verify cited sources, quotes, and statistics. Use the skill for user-directed writing and research projects, and keep sensitive unpublished drafts or private source materials out of the workspace unless you intend the agent to review them.

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 (3)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description defines a very wide set of writing-related activities without clear trigger boundaries or exclusions. In agent environments, ambiguous scope is risky because the skill may be selected for routine requests it was not meant to handle, leading to unintended behavior, context capture, or interference with safer specialized skills.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The activation examples are broad enough to match many ordinary writing requests, which can cause the skill to engage outside its intended scope. Over-broad triggering can override more appropriate system behavior, increase prompt-surface exposure, and make it easier for adversarial users to steer the agent into unnecessary research or document handling flows.

Missing User Warnings

Low

Confidence: 84% confidence
Finding: The skill encourages research and citation assistance but does not warn that generated citations or summarized sources may be inaccurate, fabricated, or insufficiently verified. This can cause users to trust unverified references, creating integrity and reputational risk, especially for technical or factual content.

Static analysis

No suspicious patterns detected.