Back to skill

Security audit

靶点药物证据评估(Target-Drug Evidence Evaluation)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language drug-target evidence triage workflow that uses declared pharma and patent MCP tools without code execution, persistence, or hidden authority.

Install only if you want a Chinese-language target/drug evidence triage workflow backed by Patsnap-style pharma and patent MCP tools. Treat outputs as early R&D/BD decision support, not clinical, investment, or legal advice, and avoid submitting confidential target or indication plans unless the configured MCP services are approved for that data.

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
  • 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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The reference description explicitly states a Chinese output template, which indicates the skill is designed to force a specific language. The file does not offer the user a language choice or document this locale restriction as an opt-in or justified regional constraint.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The default prompt invokes the skill with a generic activation phrase and no explicit scope, authorization, or task constraints. This can cause the skill to be triggered in broader contexts than intended, increasing the chance of inappropriate use, accidental invocation, or prompt-routing abuse in systems that rely on phrase matching or loose tool selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file is written entirely in Chinese and does not indicate that the user may choose another language or locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L003 states that the file defines the skill's Chinese output template and that all output must strictly follow it. This is a natural-language locale policy constraint that forces a specific language without any user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The rubric content is written entirely in Chinese, which imposes a fixed language choice on users. The file does not indicate that language selection is optional or that this locale restriction is intentional for a region-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The display name and short description are in Chinese while the default prompt is in English, but the file does not state whether the skill adapts to the user's preferred language or requires a specific locale. This can create a language/locale policy concern because the skill presentation and invocation language are inconsistent without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.