Security audit

Input Refiner

Security checks for vulnerabilities and agentic risk

Overview

This skill only rewrites user input for clarity and does not request tools, credentials, file access, network access, or persistence.

Install this if you want an agent helper for rewriting messy or long inputs into clearer instructions. Be aware it may activate for many ordinary vague or rough messages, so users should check that the refined wording still preserves their original intent.

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

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The overview says to use the skill whenever input is vague, rough, colloquial, incomplete, poorly structured, or long, which is a very broad set of common situations. Although examples are provided later, this activation guidance does not clearly constrain when this skill should be chosen over ordinary rewriting or summarization behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.