Back to skill

Security audit

Traditional Chinese Medicine

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent educational Traditional Chinese Medicine reference skill with medical-safety disclaimers and no executable or persistence behavior.

Install only if you want an educational TCM study reference. Treat herb, formula, acupuncture, pregnancy, and drug-interaction content as study material, not personal medical advice; clinical use should involve licensed healthcare professionals.

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 (5)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instructions require use of proper Pinyin with Chinese characters for all herbal names, acupuncture points, pattern names, and formula names. This imposes a specific linguistic format on outputs without indicating that users may choose another language or transliteration style.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This JSON contains parallel Chinese fields such as name_cn and name_pinyin, and later Chinese descriptions/questions, but the file itself provides no natural-language indication of how language is chosen for users. Under the policy rule, forcing or implicitly assuming a locale without user opt-in can be a language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This JSON contains user-facing natural-language fields in multiple languages, including Chinese source titles and English descriptive text, but does not indicate whether consumers should expect multilingual output or how language should be selected. For systems with language or locale policies, this can create inconsistent language behavior without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This JSON includes Chinese field values and TCM-specific naming conventions such as Chinese characters and pinyin, but provides no natural-language indication that users can opt into another language or locale. Because SQP-3 applies to all file types and covers forced language or locale constraints, this is a mild policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This JSON repeatedly pairs English syndrome names with Chinese-script and pinyin fields, which can reflect a built-in locale assumption in the skill's natural-language outputs or labels. Because the file provides no natural-language indication that users can opt in to Chinese/localized terminology, it may conflict with a language/locale policy requiring user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.