ClawHub
Back to skill

Security audit

Review Skill Improver

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only guide for analyzing review feedback and producing improvement recommendations, with no executable code or hidden privileged behavior.

Installers should treat this as an analysis/reporting skill and review any generated recommendations before applying them to review skills, especially anything related to PR generation, long-term tracking, or experiments.

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)

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 · SKILL.md (reported line 165)May include surrounding context.

md
### 2. Add Raw Function Tool Registration Exception

**Affected Skill:** `skills/pydantic-ai-common-pitfalls/SKILL.md`

**Problem:** Flagging valid pydantic-ai pattern as error

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest and main body describe this skill as analyzing feedback logs and suggesting improvements to review skills. The 'Future: Automated Skill Updates' section expands that purpose into generating PRs, tracking impact over time, and A/B testing rule variations, which are materially broader operational capabilities than log analysis and recommendation generation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.