ClawHub
Back to skill

Security audit

GitHub Actions Commit Health Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused local GitHub Actions audit tool that reads user-selected run JSON files and reports commit failure hotspots without network access, persistence, or hidden mutation.

Installers should treat this as a local reporting tool and run it only against intended GitHub Actions export directories. Review RUN_GLOB and filter environment variables before use, especially in repositories containing unrelated or sensitive JSON files.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
77% confidence
Finding
The skill processes local JSON files via a configurable glob, which gives it effective file-read capability, but it does not declare any explicit tool scope such as permissions or allowed-tools. That mismatch weakens sandboxing and review controls because an agent or platform may permit broader file access than operators expect, especially when user-controlled environment variables influence what paths are read.

Static analysis

No suspicious patterns detected.