Back to skill

Security audit

docs-skill-builder

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found no AIG issues, while Skillspector reported two low-probability findings and incomplete reference checks around a documentation-skill builder.

The scanners’ overall verdict is benign, but confidence is medium and Skillspector’s analysis is partial: several referenced paths were missing, so the evidence is incomplete. Before installing, consider whether the reported GitHub installer behavior and file and shell capabilities fit your intended use.

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
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied command delegates to a skill installer; it does not show documentation processing or skill creation. Installing an externally sourced skill is a distinct capability not disclosed by the description, and the snippet establishes no supporting relationship to the declared creation workflow. Because the repository and path are placeholders, successful installation is not established.

Content

No source excerpt is available for this finding.

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

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.