Back to skill

Security audit

kids-science-tenwan-why

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: scanners reported no AIG findings, while Skillspector flagged undeclared tool scope and broad activation examples; its review was partial.

The verdict is benign, but confidence is medium and the review was partial. Before installing, consider the broad activation examples and the undeclared tool scope. Skillspector also could not resolve a referenced output path and excluded the binary icon from some static checks, so those parts were not fully assessed.

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
  • 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.

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.

Several listed triggers describe generic video-production tasks without restricting activation to children's science content.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

These explicit trigger examples request narration timing, cartoon image prompts, voiceover annotations, or platform-specific copy without mentioning children's science or an existing session using this skill. They overlap with unrelated video-production requests and could unintentionally activate the full children's science workflow.

Content

No source excerpt is available for this finding.