ClawHub
Back to skill

Security audit

create-issues

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed GitHub issue-creation workflow with expected repository and GitHub mutations and no evidence of hidden execution, persistence, or data exfiltration.

Use this skill when you want an agent to create or synchronize GitHub Issues from approved planning documents. Before running it, confirm gh is authenticated to the intended account and repository, and review proposed issue batches or project changes when they affect public or business-critical tracking data.

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)

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The acceptance-criteria guidance states scenarios should be written as either English or pt-BR, but it does not explicitly require preserving the user's preferred language or obtaining opt-in before using pt-BR. Because this is a reusable template, that phrasing could normalize generating Portuguese-language artifacts for users who did not request that locale.

Scope Creep

Low
Category
Excessive Agency
Content
- **Registries:** use only approved corporate/organization registries — never public registries unless explicitly authorized.
- **API headers:** use the organization's standard correlation / authentication headers as defined by the API governance team.
- **Security:** do not log PII/tokens/identifiers; store secrets via the organization's secret manager; no `.env` in commit.
- **Scope:** do not invent requirements or expand scope. Stop and ask on ambiguity.
- **Architecture:** no business logic in controllers/components; domain does not access infrastructure.

## 9. Definition of Done
Confidence
75% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.