ClawHub
Back to skill

Security audit

employee-onboarding-plan

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill has limited, clearly scoped local behavior, but its script produces a basic calendar rather than the complete onboarding plan advertised.

Treat the generated calendar as a draft requiring substantial completion and HR verification of deadlines. Keep sensitive employee documents out of the input, and choose an output folder where replacing plan.md is acceptable. The optional Windows app is unnecessary for this skill and requires a separate trust decision.

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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code produces a generic weekly calendar scaffold rather than the substantive onboarding plan described. Its only scheduling logic adds seven-day intervals over a fixed 90-day horizon; it contains no onboarding workflow, owner assignment, record requirements, or US compliance logic. The appended guardrails do not supply those missing capabilities. Local input reading and output writing are ordinary supporting implementation details, and no unrelated or undeclared external activity is evident.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: 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 generated plan lacks the owners, records, and compliance deadlines promised by the manifest.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest promises a US 30/60/90-day onboarding plan with owners, records, and compliance deadlines. This loop instead generates weekly dates with an initial user-supplied focus followed by identical 'next block' placeholders; the subsequently appended guardrails do not supply the missing onboarding responsibilities or compliance schedule.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.