Thinking Framework

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 6:23 AM UTC
• Version: 1.0.4

Overview

This skill is a disclosed thinking-framework prompt package, but users should treat its psychological profiles as speculative and avoid applying them to private people.

Install only if you want an explicit framework-analysis tool. Treat claims about a person's wounds, defenses, motives, or blind spots as labeled inference, not fact; avoid using it on private individuals or for manipulation, hiring, reputation attacks, or mental-health-style judgments.

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
• YARA Signatures: Malware Match, Webshell Match, Cryptominer Match
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger logic is broad enough to activate on ordinary requests mentioning a person, organization, or movement, causing the skill to apply a speculative psychological/personality framework when the user may only want neutral analysis. In this skill's context, that is especially risky because activation leads to deep profiling instructions such as inferring wounds, drives, defenses, and blind spots, which can produce misleading or privacy-invasive outputs about living people.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill invites analysis of a target's 'psychological architecture,' 'core wound,' 'defense patterns,' and 'blind spots' without a clear upfront warning that such profiling is inferential, error-prone, and potentially inappropriate for living persons. Because the skill is explicitly designed to operationalize those profiles into subsequent reasoning, users may over-trust speculative assessments and apply them in manipulative, reputational, or privacy-invasive ways.

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium

• Category: YARA Match

Content

sessed with
   visibility often came from being unseen; people obsessed with certainty
   often came from instability)
3. Find what makes them *disproportionately reactive* — that's where the wound lives
4. Identify the early relationship patterns (family structure, key figures, major losses)
   where these patterns were first formed

**Common wound archetypes:**
```
Abandonment        : Drives fierce independence, self-sufficiency, distrust of reliance.
                     Often manifests as preemptive emotional withdrawal.
Invisibility       : Drives compulsive need for recognition, legacy, proof of impact.
                     The work is never enough because the wound is about being seen.
Inadequacy         : Drives perfectionism, overachievement, deep fear of exposure.
                     Impostor syndrome is the wound's voice.
Chaos / Instability: Drives need for control, systems, order, predictability.
                     The tighter the system, the worse the original chaos

• Confidence: 65% confidence
• Finding: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Context-Inappropriate Capability

Medium

• Confidence: 98% confidence
• Finding: The guidance explicitly instructs weaker models to emit step-by-step chain-of-thought in the user-visible response. That exposes internal reasoning traces beyond what is needed for the skill’s purpose and can lead to policy noncompliance, leakage of unsupported inferences, and easier prompt extraction of latent reasoning behavior. In this skill, which performs psychological and cognitive profiling, exposed reasoning is especially risky because it may surface speculative or sensitive inferences with undue authority.

Natural-Language Policy Violations

Medium

• Confidence: 99% confidence
• Finding: This text mandates natural-language disclosure of internal reasoning, including numbered intermediate steps before the final result. Such instructions directly push the model toward exposing hidden deliberation, which is unnecessary for applying a framework and increases the chance of unsafe disclosures, hallucinated inference chains, and policy violations. Because the skill centers on modeling people’s psychology and blind spots, those exposed steps may amplify reputational or privacy-sensitive harms.

Ssd 3

Medium

• Confidence: 99% confidence
• Finding: The file directs the model to reveal its reasoning step-by-step, including an explicit template for intermediate thought before output. This is dangerous because it trains or pressures the assistant to externalize internal deliberation, making it easier to elicit sensitive reasoning patterns and causing overexposure of speculative judgments. In this skill’s context, that danger is heightened by the subject matter: psychological inference about real people or organizations can become more harmful when the assistant lays out every inferential leap.

Static analysis

No suspicious patterns detected.