Security audit

superword

Security checks for vulnerabilities and agentic risk

Overview

This is a Word/DOCX guidance-only skill with one noisy metadata phrase that should be cleaned up but does not create a security concern by itself.

Install only if you want a DOCX/Word workflow helper. The publisher should clean up the unrelated manifest keywords, but the inspected artifact does not show code execution, data exfiltration, persistence, or destructive behavior.

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)

Vague Triggers

Medium

Confidence: 98% confidence
Finding: The manifest description includes irrelevant, noisy trigger text ('ncaa staff e ο om reputation yong qatarhend [unused864] merge obama suites sections file') that broadens or obscures the skill's activation boundary. In an agent ecosystem, this can cause inappropriate routing or accidental invocation on unrelated prompts, increasing the chance the skill handles documents it was not meant to process and weakening predictable tool selection.

Static analysis

No suspicious patterns detected.