ia-refine-prompt

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 5:14 AM UTC
• Version: 4.5.2

Overview

This skill is a prompt-refinement helper with a disclosed optional local save step and no evidence of hidden execution or data exfiltration.

This appears safe to install for prompt-refinement use. Review the optional save prompt carefully: approve writing to `.ai/PROMPT.md` only when you want a persistent local record of the refined prompt and the content does not include secrets or sensitive material.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SPEC.md (reported line 16)May include surrounding context.

md

Out of scope:
- Acting as the runtime instructions themselves (those live in `SKILL.md`).
- Trigger phrasings already covered by adjacent `ia-*` skills (`validate-plugin` flags >70% description overlap as DUPLICATE_TRIGGER).
- <!-- to fill in: domain-specific exclusions when the skill drifts -->

## Trigger Context

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The activation guidance says to use the skill when asked to "refine, improve, or sharpen a prompt" and to "make AI instructions more effective," which are broad natural-language phrases that can match many ordinary editing requests. The description does not provide explicit trigger constraints or negative examples to distinguish when this skill should activate versus a general writing or editing skill.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Persistence

After refining, offer to save the result to .ai/PROMPT.md — ask first (AskUserQuestion in Claude Code, request_user_input in Codex, numbered options in chat otherwise); never write without confirmation. If approved, append with a heading and date:

markdown

## [Prompt Name] -- YYYY-MM-DD

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The Persistence section instructs saving refined prompts to .ai/PROMPT.md after confirmation, which affects user data by storing prompt contents on disk. Although confirmation is required, the markdown does not warn that prompts may contain sensitive information or that saving creates a persistent local record.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.