Security audit

introduction-stepwise-reviser

Security checks for vulnerabilities and agentic risk

Overview

This skill is a research-introduction editing helper that transparently creates two Markdown output files and shows no hidden execution or data-exfiltration behavior.

Before installing, expect the skill to create two Markdown files when used. If you only want an in-chat revision or want different paths, tell the agent that explicitly before invoking the skill.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill instructs the agent to always write two Markdown files to disk, including inferred filenames and locations, without requiring user confirmation or clearly warning about where files will be created. This can cause unintended local file creation, overwrite surprises, or disclosure of processed research text into the working directory or alongside source files, especially when the user expected an in-chat rewrite only.
Content: No source excerpt is available for this finding.