ClawHub
Back to skill

Security audit

IRIS代码格式化专业版

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only IRIS/ObjectScript code review and formatting skill whose command examples are mostly purpose-aligned, but users should treat its broad operation wording as requiring explicit confirmation before changes.

Install only if you want an agent to help review and format IRIS/ObjectScript projects. Keep it pointed at explicit project directories, review generated shell commands before running them, and require a dry-run or confirmation before any formatting, reset, import, save, or delete-style action.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
88% confidence
Finding
The skill is presented as a narrowly scoped code review/formatting tool, but its documented interface includes generic create/query/modify/delete and import/reset operations. That scope expansion increases the chance an agent will treat unrelated file or project state changes as in-scope, enabling unintended destructive actions under a trusted maintenance workflow.

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill declares exec capability in a context that primarily needs file reading, pattern matching, and report generation. Exposing shell execution broadens the attack surface significantly because later instructions or user-controlled paths can be routed into command execution flows, especially in an agent environment that may trust tool-described workflows.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The activation scope is defined by a long, fuzzy keyword list without meaningful boundaries, exclusions, or negative examples. In agent systems, this can cause over-triggering on unrelated prompts and inappropriate invocation of powerful tooling, increasing the risk of unintended file operations or misleading authority transfer to the skill.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill describes automatic create/modify/delete, import, and reset style operations without prominent warnings or consent requirements. In a code-governance tool, users may reasonably expect analysis-only behavior, so hidden or underexplained mutation capability can lead to accidental code changes, report overwrites, or destructive resets.

Static analysis

No suspicious patterns detected.