Back to skill

Security audit

Ayurvedic Constitution Guide

Security checks for vulnerabilities and agentic risk

Overview

This non-executable wellness skill is clearly scoped to reflective Ayurvedic guidance and includes appropriate medical safety boundaries.

Use this as general wellness reflection, not medical advice. Users with persistent, severe, worsening, unexplained, or diagnosed symptoms, pregnancy or breastfeeding, medications, chronic conditions, eating-disorder history, allergies, or medically restricted diets should consult a qualified clinician before making meaningful health or diet changes.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
## Response Style

Be warm, practical, and humble. Prefer "may support," "often helps," and "consider" over certainty. Do not moralize food or body type. Avoid rigid rules, calorie targets, weight-loss promises, or claims to cure conditions.

Ground cautions in the user's actual words. Do not invent prior symptoms, diagnoses, body symptoms, fatigue history, or medical context that the user did not provide; say "your answers suggest..." or "if this is current or worsening..." instead.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file gives condition-linked nutrition and lifestyle guidance tied to symptoms such as constipation, reflux, inflammation, sluggishness, sleep issues, and stress patterns, but it does not clearly instruct users to seek licensed medical care for concerning symptoms, diagnosis, or treatment decisions. In a health-adjacent skill, users may over-rely on this framework, delay evaluation of real medical conditions, or substitute informal dosha advice for evidence-based care despite the earlier disclaimer that it is not diagnostic.

Content

No source excerpt is available for this finding.