ClawHub
Back to skill

Security audit

Iterative Code Evolution

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent coding-methodology guide that writes local project progress logs, with no evidence of hidden execution, exfiltration, or unrelated privilege use.

Install only in repositories where local experiment logs are acceptable. Add `.evolution/` to `.gitignore` for private work, review log contents before sharing, and keep credentials or sensitive production data out of archived failure notes and variants.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Skill Enumeration

Medium
Category
Agent Snooping
Content
cp SKILL.md ~/.claude/skills/iterative-code-evolution.md

# Per-project (available only in that project)
mkdir -p your-project/.claude/skills
cp SKILL.md your-project/.claude/skills/iterative-code-evolution.md
```
Confidence
85% 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.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The README explicitly states that the skill maintains a persistent `.evolution/` directory and logs variant history, scores, and lessons learned, but it does not warn users that local project data will be stored over time. While this is not inherently malicious, silent persistence can expose sensitive codebase details, failed experiment traces, or internal reasoning artifacts to other local users, backups, or accidental commits.

Missing User Warnings

Low
Confidence
85% confidence
Finding
The skill directs users to persist an `.evolution/log.json` file containing descriptions of code changes, failure modes, test behavior, and learned principles, but provides no warning to avoid including secrets, proprietary code details, sensitive paths, or production data. In environments where codebases or debugging outputs contain confidential information, this can create an unintended local data-retention trail that may later be committed, shared, or exposed.

Static analysis

No suspicious patterns detected.