Skills/ClawHub/aky-tcm-prescription

aky-tcm-prescription@2.0.0

CAUTION· static only

Publisher claims: "AI-powered Traditional Chinese Medicine (TCM) prescription assistant based on classical texts: Shanghan Lun (伤寒论), Jingui Yaolue (金匮要略), and Formula Study (方..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher wangfromchu-ai · publishing for 167 daysInstalls 869Last detonated 5 h ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-14 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Prompt injectionreferences/constitution-clinical.md:37 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| 血瘀质 | +Dan Shen (丹参), Chuanxiong (川芎), Taoren (桃仁) |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/formula-database.md:227 · Prompt injection — known jailbreak technique reference · informational: not an instruction file### Wen Dan Tang (温胆汤) — Gallbladder-Warming DecoctionFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/syndrome-differentiation.md:98 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| 痰火扰心 | Mania, laughing/crying, insomnia, delirium, red face | Red, yellow greasy | Slippery, rapid (滑数) | Wen Dan Tang (温胆汤) / Goun Teng Yin |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/formula-database.md:287 · Prompt injection — known jailbreak technique reference · informational: not an instruction file### Tianwang Buxin Dan (天王补心丹) — Heavenly Emperor Heart-Supplementing PelletFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/syndrome-differentiation.md:95 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| 心阴虚 | Palpitations, insomnia, low-grade fever, night sweats, dry mouth | Red, little coating | Thin, rapid (细数) | Tianwang Buxin Dan (天王补心丹) |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,924 tok
1 file · 9 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim wangfromchu-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim wangfromchu-aiPropose a patch to the maintainer