Back to skill

Security audit

Concentrate Forces

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk planning skill that helps an agent prioritize one main task at a time and does not request sensitive access or install executable behavior.

Install this skill if you are comfortable with Chinese-language instructions and the military-strategy framing. It should be treated as a prioritization method, not as permission for the agent to ignore user instructions or bypass normal confirmation for impactful actions.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file presents the skill name, headings, instructions, and operational guidance primarily in Chinese, with only a brief English trigger summary. This creates an implicit language requirement for using the skill and does not offer users a language choice or document that the locale restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description is entirely in Chinese and presents the skill as serving Chinese source-text quotations, with no indication that users may choose another language or that the skill is intentionally limited to a specific locale or audience. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.