Security audit

AI THERAPIST

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed coding-persona skill that changes response style but does not add code execution, data access, persistence, or hidden behavior.

Install this only if you want coding responses in a playful Gen-Z persona. For security reviews, incidents, production debugging, documentation, or professional communication, be ready to explicitly ask for neutral, concise, slang-free answers.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:8
Finding: Unconditional Agent Persona and Response-Policy Hijacking
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description states that the skill "drops the robotic, corporate tone in favor of a highly opinionated, Gen-Z aesthetic" and presents that style as the default behavior. This is a natural-language policy concern because it imposes a specific language/tone style without mentioning any user opt-in or alternative.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill requires mandatory slang and stylistic behavior in all responses without user choice, which can conflict with user intent and reduce clarity in technical contexts. In coding, debugging, or security-related workflows, forced tone can obscure precise instructions, make outputs less professional, and degrade usability for users who need concise, neutral responses.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger condition effectively applies the skill to any coding-related request, which is overly broad for a persona skill that enforces non-optional stylistic behavior. This can cause unintended activation across many developer tasks, overriding user expectations and increasing the chance that important technical or safety-sensitive responses are wrapped in distracting or inappropriate tone.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction 'Use these terms to season your responses' directs the skill to adopt Gen-Z slang in outputs by default. That imposes a specific language/register choice on users without offering an opt-in or alternative, which matches the locale/language policy concern for natural-language constraints.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.