Security audit

discussion-grammar-diagnosis

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow grammar-diagnosis skill for research-paper Discussion sections, with only minor routing-risk from broad trigger phrases.

Installers should understand that this skill is meant for grammar diagnosis of Discussion sections in psychology research papers. Its broad trigger terms may make it appear for general grammar requests, so users should confirm the context before relying on its output.

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 (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger list includes broad phrases such as "grammar check" and "tense diagnosis," which can cause the skill to activate outside its intended scope. This may route unrelated user content into a narrow Discussion-specific diagnostic flow, creating incorrect behavior, user confusion, or accidental handling of content the skill was not designed to assess.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrase "grammar check" is broad and likely to match many general writing-assistance requests outside this skill’s stated scope of Discussion-section grammar diagnosis for psychology papers. Over-broad activation can cause unintended routing, making the agent invoke this skill in inappropriate contexts and potentially suppress more suitable tools or produce misleading advice.

Static analysis

No suspicious patterns detected.