Decide

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 5:31 PM UTC
• Version: 1.0.1

Overview

This skill keeps local decision notes and asks the agent to be more conservative about major choices, with no evidence of exfiltration, hidden execution, or destructive behavior.

Install only if you want the agent to keep persistent local notes about decision patterns in ~/decide/. Review the first-run setup because it creates local files, and do not store secrets, credentials, or copied private third-party data in the decision memory.

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

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

Line L003 says to use this file whenever ~/decide/ is missing or empty, but it does not define narrower context about what user intent or workflow should invoke the setup. That can cause unintended activation whenever the folder state matches, even if the user did not ask to initialize this skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The setup directs immediate creation of directories/files and permission changes in the user's home directory without an explicit warning or approval gate. In an agent context, automatic filesystem modification can violate user expectations, create persistence, and be abused to write state silently before the user understands what is being installed.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium

• Category: Privilege Escalation
• Confidence: 80% confidence

Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

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

bash

mkdir -p ~/decide/domains
touch ~/decide/{memory.md,decisions.md}
chmod 700 ~/decide ~/decide/domains
chmod 600 ~/decide/{memory.md,decisions.md}

Sudo/Root Execution

Medium

• Category: Privilege Escalation
• Confidence: 80% confidence

Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · setup.md (reported line 17)May include surrounding context.

mkdir -p ~/decide/domains touch ~/decide/{memory.md,decisions.md} chmod 700 ~/decide ~/decide/domains chmod 600 ~/decide/{memory.md,decisions.md}

text

If `~/decide/memory.md` is empty, initialize it from `memory-template.md`.

Missing User Warnings

Low

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

Finding

This markdown file instructs the user to create a new directory and file under ~/decide/, which changes local user data. While the steps are framed as 'Safe Migration,' there is no explicit warning that following them will modify the filesystem or create persistent files in the user's home directory.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.