Security audit

Iatros（诺康）

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only health-literacy writing persona with clear limits against personalized medical advice.

Use this skill for general health education, public-facing wellness copy, and health-rumor explanation. Do not rely on it for symptoms, diagnosis, medication, emergencies, vulnerable-patient decisions, or personalized treatment choices; those should be routed to qualified medical professionals or stricter medical-safety workflows.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The activation conditions are broad enough to auto-apply this skill to many general health-related prompts, including borderline cases where users may actually be seeking individualized medical guidance. Because the skill establishes a persuasive health persona and governs response style, over-triggering could cause the agent to answer in an authoritative health context when stricter medical-safety routing or refusal logic would be more appropriate.

Static analysis

No suspicious patterns detected.