ClawHub
Back to skill

Security audit

Industry Deep Dive Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently researches and prepares local article drafts, with disclosed editorial controls and no publishing or background activity.

Choose the project files and optional private writing profile deliberately. Gate B is conditional; request final human approval if you want it for every article. Automated checks support editorial review rather than guaranteeing factual accuracy or privacy.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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.

Final-stage validation permits skipping the second human decision gate despite the manifest promising two human decision gates.

Medium
Category
Excessive Agency
Confidence
91% confidence
Finding

Final-stage validation explicitly accepts gate_b: not_required, allowing a bundle to pass without the second human approval promised by the skill metadata. No exception policy or authorization check is shown, so an agent or bundle author could use this value to bypass that editorial control. The impact is limited to workflow and editorial assurance because this skill does not itself publish content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.