ClawHub
Back to skill

Security audit

GitHub Actions Deploy Risk Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local GitHub Actions deployment-risk report generator with proportionate file-reading behavior and no evidence of hidden network, persistence, or destructive actions.

Install this only where reading the selected GitHub Actions JSON exports is acceptable. Keep RUN_GLOB narrow, and review JSON output before sharing because it may include repository names, branches, workflow names, run timing, and sample run URLs.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding

The skill reads local GitHub Actions JSON artifacts and invokes shell/Python-capable scripts, but it does not declare any explicit tool scope such as permissions or allowed-tools. That omission weakens least-privilege guarantees and makes it harder for a host agent to constrain what the skill may access, especially if the implementation evolves or is invoked in a broader environment than intended.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This code ingests run artifacts and later prints extracted metadata, including repository identifiers and URLs, which may expose internal project structure or operational details. Although the script's purpose is auditing deploy risk, there is no explicit disclosure in comments or docstrings that these details will be surfaced in output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.