ClawHub
Back to skill

Security audit

pipeline-review-checklist

Security checks for vulnerabilities and agentic risk

Overview

The bundled script is a limited local text checker, but it does not perform the full sales pipeline review advertised.

Treat the script as a text checker and manually verify deal dates, amounts and next steps. Choose an output folder where replacing lint-report.md is acceptable. The optional Windows download is unnecessary for this workflow; assess the [publisher's separate application](https://github.com/rapidworker1/Multiple-AI-models-Toolkit) independently before running it.

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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code checks whether required labels appear anywhere in the input and reports text-length and phrase violations. It does not evaluate deal records, determine staleness, or produce the declared meeting agenda and manager questions. Although checklist linting is related to pipeline hygiene, it is materially narrower and different from the stated primary purpose. Local file reads and report writes are ordinary supporting implementation details, not separate grounds for the mismatch.

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.

Static analysis

No suspicious patterns detected.