Lobster Farmer Feeder

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 3:31 AM UTC
• Version: 0.1.2

Overview

This skill is a small, disclosed helper for a local Lobster Farmer game CLI and does not show hidden data access, persistence, exfiltration, or destructive behavior.

Install this only if you use the Lobster Farmer local CLI and are comfortable with the agent checking status, starting the local service, and running feed commands you request. Review the model and token values before batch-feeding because they mutate local game state.

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
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

External Model or Provider Selection

High

• Category: Excessive Agency
• Confidence: 90% confidence

Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

• Feed one lobster:

bash

lobster-farmer feed --model gpt-4.1 --input-tokens 800 --output-tokens 400

• Feed with emotion:

External Model or Provider Selection

High

• Category: Excessive Agency
• Confidence: 90% confidence

Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

• Feed with emotion:

bash

lobster-farmer feed --model gpt-4.1 --input-tokens 800 --output-tokens 400 --emotion "focused"

• Feed different models:

External Model or Provider Selection

High

• Category: Excessive Agency
• Confidence: 90% confidence

Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

• Feed different models:

bash

lobster-farmer feed --model claude-3.7 --input-tokens 1200 --output-tokens 300
lobster-farmer feed --model qwen-max --input-tokens 600 --output-tokens 200

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 87% confidence

Finding

The manifest description says to use this skill when the user asks to 'feed a lobster,' 'simulate model usage,' or 'update growth state and emotion,' which are fairly broad natural-language triggers. It does not provide negative examples or narrower activation boundaries, increasing the chance of unintended invocation from ordinary conversational requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.