ClawHub
Back to skill

Security audit

Dev Workflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed development-workflow orchestrator, but it can be triggered broadly and then drive code, testing, GitHub issue, PR, and merge-related actions with limited per-step user control.

Install only if you want an agent to manage an end-to-end development workflow. Before using it, require explicit confirmation before code changes, GitHub comments, issue closure, PR creation, and any merge-related action, especially when you only asked for planning or next steps.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation criteria are extremely broad and include common development phrases like starting a feature, asking for the next step, or mentioning an issue. In an autonomous skill that can orchestrate planning, coding, testing, and PR actions, this increases the chance of accidental invocation and unintended repository operations without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The session-start instruction hardcodes the opening user-facing prompt in Portuguese: "Nova feature ou continuando uma issue existente?" This imposes a language choice without user opt-in and does not document a justified locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.