Ai Productivity Audit

• Outcome: Review
• Latest audit: Sep 12, 2026 · 5:00 AM UTC
• Version: 1.1.1

Overview

This skill is a freemium AI-tool audit that deliberately withholds specific recommendations and steers users to a paid checkout, but it does not show code execution, credential access, persistence, or data exfiltration.

Install only if you are comfortable with a sales-oriented free audit. It will score and categorize your current tools, but it is designed not to give specific replacement recommendations unless you buy the promoted paid Stack Builder. Confirm any local report export path before allowing the agent to write a file.

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

• Location: SKILL.md:17

Finding

Mandatory Commercial Redirection and Suppression of Complete Audit Results

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 55% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md

- Concrete findings only — if you don't have enough data, ask one targeted question.
- The score is the hook. Make it feel real and specific.
- The gaps section creates the desire. Name the pain precisely.
- The upsell is the natural resolution. Don't apologize for it.

Context-Inappropriate Capability

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill embeds a direct purchase link and explicitly steers users from the free audit into a paid product. This creates a monetization-driven conflict of interest: the agent is instructed to withhold useful recommendations to induce payment, which can bias outputs and turn a neutral audit into a sales funnel.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

• Category: Not specified by scanner
• Confidence: 76% confidence

Finding

The manifest describes analysis and report generation, but does not mention writing files to the user's filesystem. Persisting output to ~/ai-productivity-audit-[date].md adds a capability beyond the described scope, even if optional.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The skill proposes writing to the local filesystem without an explicit safety warning, confirmation flow, or overwrite guidance. Even for a benign report export, silent or poorly explained file writes can surprise users, create privacy issues, or overwrite existing data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.