Back to skill

Security audit

wechat-article-beautify

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the completed scan reported no AIG issues, while Skillspector noted concerns about undeclared tool scope and automatic dependency installation; some referenced paths were unresolved, so the evidence is incomplete.

The verdict is benign, but confidence is medium and the Skillspector scan is partial: three path-like references were unresolved. Before installing, consider whether you are comfortable with the reported automatic Playwright and Chromium installation and with file access when runtime permissions are unknown.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The workflow automatically installs dependencies without warning the user about changes to their environment.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The workflow directs the agent to install Playwright and download Chromium when prerequisites are missing, without first obtaining approval for environment changes. Although these are legitimate screenshotting dependencies, unpinned installation can introduce supply-chain exposure or dependency conflicts, especially if the referenced managed environment is shared with other workflows.

Content

No source excerpt is available for this finding.