LogoClawIndex
CasesSkillsAbout
LogoClawIndex

vet-untrusted-project - Audit an untrusted project before execution

Statically assesses an unfamiliar repository for credible signs of attacks against developers, coding agents, workstations, credentials, or shared systems.

Tags

Updated: 2026-10-16
repository audituntrusted projectsmaliciousness assessmentagent safety

Capabilities

Inventory project filesReview execution surfacesAssess repository attack chainsClassify maliciousness or compromise

Typical Inputs

Project directory pathsRepository filesProject configuration

Typical Outputs

Maliciousness classificationCredible attack chainsAudit coverage summary

What this skill does

  • Inventory project files
  • Review execution surfaces
  • Assess repository attack chains
  • Classify maliciousness or compromise
  • Report audit coverage gaps

Inputs

  • Project directory paths
  • Repository files
  • Project configuration
  • Dependency metadata

Outputs

  • Maliciousness classification
  • Credible attack chains
  • Audit coverage summary
  • Read-only enforcement status
  • Inconclusive audit status

Requirements

  • Read-only target access
  • Neutral trusted directory
  • Python 3 standard library
  • No target-code execution
  • No sandbox escalation

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.