ClawHub
Back to skill

Security audit

fec-refactoring

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward behavior-preserving refactoring workflow with disclosed local code-reading, editing, verification, and rollback guidance.

Install this only if you want an agent to perform disciplined local refactoring. Expect it to read relevant project files, run tests or builds, and modify code within the requested scope; review the proposed diff budget and verification results before accepting broad or risky changes.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 10)May include surrounding context.

md
- ID: `fec-refactoring`
- Category: `review-quality`
- Version: `2.9.0`
- Source: `skills/fec-refactoring/SKILL.md`

## Description

Session Persistence

Medium
Category
Rogue Agent
Confidence
55% 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 · references/principles.md (reported line 13)May include surrounding context.

md
2. **Green Baseline First:** distinguish pre-existing failures from regressions introduced by the current step.
3. **One Refactoring at a Time:** keep each step attributable to one structural intent.
4. **Verify Every Step:** use feedback at the smallest useful scope before continuing.
5. **Revert Before Repairing:** a new regression invalidates the current step; restore the previous state before redesigning it.
6. **Separate Feature Work:** new outcomes, changed rules, or changed error behavior are not pure refactoring.
7. **Smallest Safe Refactoring First:** prefer a reversible local change over a speculative redesign.
8. **Stay Within the Diff Budget:** scope growth is a stop signal, not permission to keep expanding.

Static analysis

No suspicious patterns detected.