Back to skill

Security audit

观众旅程设计

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language story-planning workflow that reads project planning files and writes a fixed audience journey map output.

Install this if you want a Chinese-language audience-journey planning workflow. Before running it, be aware that it reads multiple project planning documents and writes the resulting map to CLAW_WORKSPACE/99-汇总/audience-journey-map.md, so review or back up any existing file at that path if overwrites matter.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is written entirely in Chinese and presents the skill behavior and triggers only in that language context, aside from a few English terms. The file does not state that the skill is region-specific or offer an opt-in choice of language/locale, which can violate organizational language-choice policy.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the agent to write directly to CLAW_WORKSPACE/99-汇总/audience-journey-map.md without an explicit warning that running the skill will modify workspace files. Undisclosed file writes can surprise users, cause unintended overwrites, and make it easier for downstream workflows to alter project state without informed consent, though the path here is fixed and contextually related to the skill's purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.