ClawHub
Back to skill

Security audit

GitHub Actions Retry Recovery Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill locally analyzes user-provided GitHub Actions run JSON exports and does not show hidden network access, persistence, credential handling, or destructive behavior.

Installers should expect the skill to read GitHub Actions run JSON files matched by RUN_GLOB and include private repository metadata in its reports if those files contain it. Keep RUN_GLOB limited to the intended exports, and use FAIL_ON_CRITICAL only when a nonzero CI exit is desired.

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding

The skill declares executable/scripted behavior and implicitly reads local files via RUN_GLOB, but it does not declare any tool scope such as permissions or allowed-tools. That mismatch can cause the skill to run with broader-than-expected ambient capabilities in some agent environments, weakening least-privilege controls and making review harder.

Content

No source excerpt is available for this finding.