Back to skill

Security audit

tcm-diagnosis-efficacy-standard-2024

Security checks for vulnerabilities and agentic risk

Overview

The skill is a static Chinese TCM reference, but it lacks medical safety guardrails despite covering serious and emergency conditions.

Review this skill as a medical reference, not a diagnosis tool. Before installing, ensure your agent is instructed to treat the material as informational, recommend licensed clinical care for diagnosis and treatment, and direct urgent symptoms such as snakebite, tetanus signs, burns, severe infection, fractures, breathing trouble, neurologic symptoms, suspected cancer, or sick infants/children to immediate professional care.

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 (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description and invocation guidance are written as directives to use the skill for Chinese-language queries about TCM diagnoses, with no indication that users may interact in another language or choose a locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

SQP-3 applies to all file types and flags natural-language language/locale policy violations. This file presents all user-facing content in Chinese only, with no indication that the skill is region-specific or that users can opt into a Chinese locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The entire skill file is written in Chinese and presents its content without any indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or China-specific workflow. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This file provides extensive disease descriptions, diagnostic criteria, syndrome classifications, and efficacy standards for many serious conditions without any user-facing warning that the material is reference information rather than medical advice. Because it covers acute and potentially life-threatening conditions such as tetanus, toxic snakebite, gangrene, burns, deep infections, and cancer, a user could rely on the content for self-diagnosis or delay urgent professional treatment, increasing the safety risk well beyond ordinary informational content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file presents all instructions and medical content exclusively in Chinese, and nowhere indicates that the user can choose another language or that the content is intentionally limited to a Chinese-speaking audience. Under the policy rule for language or locale constraints, forcing a single language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all user-facing content in Chinese without indicating opt-in, alternative language availability, or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file consists wholly of Chinese-language medical content and does not indicate that users may choose another language. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file is written entirely in Chinese and presents all instructions and clinical content in a single language with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file is entirely written in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.