ClawHub
Back to skill

Security audit

Cicd Playbook

Security checks for vulnerabilities and agentic risk

Overview

This skill is a CI/CD documentation template that guides users to write safer deployment playbooks and does not execute deployments or modify systems.

This appears safe to install as a documentation helper. Review generated playbooks before adopting them operationally, especially any rollback authority, approval rules, secret-management steps, and placeholder deployment commands, because those are templates that must match your real production 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 181)May include surrounding context.

md
**Required for:** [Production deploys / deploys affecting >X% of traffic / deploys to specific regions]
**Who can approve:** [e.g. Any engineer on the team / Lead engineer / On-call engineer]
**Approval timeout:** [e.g. 24 hours — auto-cancelled if no approval]
**How to approve:** [GitHub Actions approve step / Slack command / other — with link]

**When to withhold approval:**

Static analysis

No suspicious patterns detected.