Decision Engine

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:41 PM UTC
• Version: 1.0.0

Overview

This is a Markdown-only decision-support skill with no hidden code, credential access, persistence, or unsafe execution behavior found.

Safe to install for decision coaching. Be aware that its broad phrases like 'What am I missing?' may cause it to apply decision frameworks in ordinary conversations, so invoke it deliberately when you want structured decision support.

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

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Memory Poisoning: Persistent Context Injection, Context Window Stuffing, Memory Manipulation
• 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

Findings (6)

Memory Manipulation

High

• Category: Memory Poisoning

Content

### Decision Brief YAML Template
```yaml
decision:
  title: "[Clear statement of what we're deciding]"
  type: 1|2|3|4
  owner: "[Person accountable for the decision]"
  deadline: "YYYY-MM-DD"

• Confidence: 80% confidence
• Finding: Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Memory Manipulation

High

• Category: Memory Poisoning

Content

### Decision Brief YAML Template
```yaml
decision:
  title: "[Clear statement of what we're deciding]"
  type: 1|2|3|4
  owner: "[Person accountable for the decision]"
  deadline: "YYYY-MM-DD"

• Confidence: 80% confidence
• Finding: Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The invocation example "Help me decide whether to [your decision]" is a very general natural-language phrase that could easily appear in ordinary conversation outside a narrowly scoped skill context. The README does not provide tighter trigger constraints, alternate exact phrases, or exclusion conditions to distinguish intended activation from incidental use.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

### Examples of Good Policies
- **Hiring**: "If a candidate scores <7/10 on the technical interview, automatic no. No exceptions."
- **Spending**: "Any expense under $500 that's in the approved budget — auto-approve, no meeting needed."
- **Pricing**: "We don't discount more than 15%. If the deal requires more, we walk."
- **Meetings**: "No meeting without an agenda and a decision to be made. Cancel if no agenda 24h before."
- **Technical**: "If we can buy for <3x the cost of building, we buy."

• Confidence: 85% 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.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill defines very broad natural-language invocation phrases such as 'Help me decide [X]' that can overlap with ordinary conversation. In an agent environment, this can cause unintended activation and execution of the skill in contexts where the user did not explicitly intend to invoke a decision-support workflow, creating prompt-scope confusion and potential data over-collection.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Several listed commands are generic phrases like 'What am I missing?' or 'Score this decision,' which are common conversational utterances and lack constraints tying them to this skill specifically. This increases the chance of accidental triggering, context hijacking, or applying the decision framework to unrelated conversations without clear user intent.

Static analysis

No suspicious patterns detected.