Back to skill

Security audit

中医舌诊(Tongue Diagnosis)

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only tongue-photo diagnosis skill, but its medical-diagnosis framing and broad health trigger warrant review before use.

Install only if you want a Chinese-language TCM tongue-observation aid, not a reliable diagnostic tool. Do not use it to rule in or rule out illness, delay care, handle urgent symptoms, or choose medication; keep uploaded mouth photos private and consult a qualified clinician for health concerns.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
77% confidence
Finding

The file presents the skill entirely in Chinese and provides no indication that output language should follow the user's preference or be configurable. Under the policy, locale or language constraints should either be optional for the user or explicitly justified as region-specific; neither is stated here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad medical and wellness terms such as '健康评估' alongside common tongue-related phrases, which can cause the skill to activate in conversations that are only generally about health rather than explicitly requesting tongue-image analysis. In a medical-diagnosis context, unintended invocation is more dangerous because it may lead users to receive quasi-diagnostic guidance without clear consent or appropriate context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This file presents detailed medical diagnostic claims linking tongue features and tongue fissure locations to specific organ diseases and prognosis, but provides no warning that the content is not validated medical advice and not a substitute for professional evaluation. In the context of a skill explicitly intended to let users upload tongue photos for diagnosis, this omission materially increases the risk that users will rely on unreliable or non-evidence-based guidance, delay care, or make harmful health decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all user-facing output exclusively in Chinese, including headings, report sections, and warnings. Under the policy rule for natural-language violations, forcing a specific language without offering choice or documenting a justified locale constraint is a reportable issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This file presents all instructional and reference content solely in Chinese and does not provide user opt-in, alternatives, or justification for enforcing that language.

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 instructional content only in Chinese, with no indication that the skill is region-specific or that users can opt into this language, which may conflict with organizational language-choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file consists solely of Chinese-language instructions and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the natural-language policy rules, forcing a specific language without opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.