ClawHub
Back to skill

Security audit

坤如玛丽保胎知识库

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language healthcare operations writing skill with compliance guardrails and no executable code, persistence, credential use, or external data access.

Install only if you want Chinese-language marketing and operations drafts for this specific healthcare center. Treat generated material as drafts that need human medical, legal, and advertising-compliance review before publication or patient use.

A.I.G

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

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises activation on a wide set of loosely scoped keyword mentions such as brand names, service category terms, and generic requests for marketing materials. This can cause the skill to trigger in unintended contexts, leading the agent to inject domain-specific medical marketing content when the user did not explicitly request this skill, which is especially risky because the subject matter involves healthcare and patient-facing claims.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file is entirely framed as a mandatory brand voice standard in Chinese and states that all operational content must follow it before generating any content. This imposes a specific language/locale style without any opt-in or explicit justification that the skill is limited to Chinese-language use cases.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file appears to require Chinese as the only operating language for the skill’s core reference content. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template defines broad trigger phrases for generating social-media content without clear gating on user intent, role, or approved use context. In a skill designed for automated marketing copy, this can cause unintended activation and production of persuasive medical marketing content in response to loosely related prompts, increasing the risk of policy bypass, misrouting, and misuse in sensitive healthcare communications.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The sales/support script section is framed for multiple customer-contact scenarios but lacks a precise activation boundary indicating when the skill should provide standardized persuasive responses versus neutral information. In a healthcare operations skill, this ambiguity can lead to unsolicited generation of sales-oriented or quasi-medical guidance in the wrong context, which may mislead users or create compliance issues.

Content

No source excerpt is available for this finding.