ClawHub
Back to skill

Security audit

Ci Cd Compliance

Security checks for vulnerabilities and agentic risk

Overview

This is a simple CI/CD guidance skill; the staging auto-deploy language describes a policy and does not add code, credentials, persistence, or autonomous deployment capability.

Review the missing referenced file if the publisher later includes it, since this package currently only contains the top-level CI/CD rules. As inspected, the skill is safe to use as policy guidance, but production deployment should still remain tied to your repository's normal tag and approval controls.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: ci-cd-compliance
description: CI/CD pipeline requirements and deployment standards. Use when (1) Setting up CI/CD pipelines, (2) Debugging CI failures, (3) Configuring deployment workflows, (4) Managing staging/production releases, (5) Investigating build failures. Covers CI gate requirements, merge policies, auto-deploy to staging, production approval process.
---

# CI/CD Compliance Rules

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
## Merge Policy

* **Merge only if green**
* Auto-deploy to **staging** on merge
* Production requires tag/approval

## CI Failure Handling

Static analysis

No suspicious patterns detected.