Military Civilian Talent (EN)

• Outcome: Review
• Latest audit: Sep 16, 2026 · 6:20 AM UTC
• Version: 2.0.0

Overview

This is a markdown-only educational skill, but it includes broad, actionable military fieldcraft and hazardous practical templates without tight enough limits.

Install only if you want a broad reference skill and are comfortable supervising high-risk topics. Do not rely on it for tactical military help, structural or electrical work, pesticide application, machinery repair, or food preservation without authoritative local guidance and qualified professionals where appropriate.

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 (9)

Natural-Language Policy Violations

High

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

Finding

This file includes structured military-oriented guidance on terrain advantages, vulnerabilities, tactical uses, camouflage, infiltration-related concealment concepts, and field water procurement. While framed as knowledge content, it can directly support operational planning or evasion behavior, and the dual-use/military framing makes the misuse path more plausible than in a purely historical or academic context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

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

Finding

The food preservation template gives procedural guidance for preserving meat, fish, fruits, and vegetables, including fermentation, smoking, and canning-like safety checks, but it does not prominently warn that incorrect preservation can cause serious foodborne illness such as botulism. Because users may treat the template as sufficient operational guidance, omission of an explicit health-risk warning can lead to unsafe preservation decisions based on incomplete context or incorrect assumptions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The machinery troubleshooting template provides diagnostic and repair steps for tractors, diesel engines, pumps, and electric motors, which can expose users to crush, entanglement, fire, stored-energy, and electrical hazards. Although it mentions safety precautions and referral to a mechanic, it lacks a clear up-front warning that AI-generated repair instructions may be incomplete or wrong and that performing repairs can cause serious injury or death.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

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

Finding

The construction template requests step-by-step procedures for walls, roofs, buildings, repairs, and foundations without an explicit warning that structural work can cause collapse, falls, and serious injury if the design or execution is wrong. In this context, users may rely on generic AI instructions for load-bearing or code-regulated work, increasing the chance of unsafe construction and latent structural defects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

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

Finding

The pest management template asks for specific chemical products, dilution, and pre-harvest intervals but does not explicitly warn about toxicity, protective equipment, drift, environmental harm, residue limits, or legal restrictions on pesticide use. In an agriculture-focused skill, this omission is especially dangerous because the template encourages actionable pesticide instructions that users may apply directly, potentially causing poisoning, crop contamination, or regulatory violations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The trigger scope is broad and covers generic domains like agriculture, construction, electrical repair, accounting, and military topics without meaningful activation boundaries. This can cause the skill to engage in many unrelated or higher-risk contexts, increasing the chance it will provide sensitive dual-use or hazardous guidance when not specifically intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

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

Finding

The preservation section gives actionable room-temperature fermentation, salting, and oil-preservation instructions, including multi-day ambient processes, but omits critical food-safety constraints such as sterilization, salt/acidity thresholds, refrigeration boundaries, and botulism/contamination warnings. In a user-facing assistant, this could cause unsafe preparation of low-acid foods and create a realistic risk of foodborne illness from users following incomplete guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

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

Finding

The schema sets language: en, and the changelog notes the skill was rewritten in English, but the file does not offer a language choice or explain why English is required. This is a natural-language policy concern because it imposes a locale preference without explicit user opt-in.

Content

No source excerpt is available for this finding.

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 70% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/method-patterns.md (reported line 268)May include surrounding context.

md

| E001 | Safety-critical information requested | Add safety warnings, recommend professional |
| E002 | Construction/electrical code question | Recommend local code authority |
| E003 | Agricultural chemical emergency | Recommend professional consultation |
| E004 | Specialized equipment beyond scope | Recommend manufacturer or specialist |
| E005 | Complex financial/business analysis | Recommend accountant or business advisor |

Static analysis

No suspicious patterns detected.