ClawHub
Back to skill

Security audit

Subagent Driven Development

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed development workflow for using subagents to implement, test, review, and commit planned code changes in an isolated workspace.

Install only if you want an agent to carry out a full implementation plan in your repository, including file changes, tests, reviews, and commits. Start from an isolated worktree or non-main branch and make commit permission explicit before invoking the workflow.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly instructs implementer subagents to implement, test, commit, and self-review, but it does not prominently warn that following the workflow will modify repository state and may create commits automatically. In an agentic workflow, that omission can cause users to invoke the skill without realizing it performs state-changing actions, increasing the chance of unintended code changes or commits in the wrong repository or branch.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md
"Mark task complete in TodoWrite" [shape=box];
    }

    "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
    "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];

Static analysis

No suspicious patterns detected.