ClawHub
Back to skill

Security audit

Inert Context-Shadowing Review Control

Security checks for vulnerabilities and agentic risk

Overview

This is an inert Markdown-only security review test specimen with no executable behavior, persistence, credential access, or network use.

Installing this skill should only expose the agent to static review text. Users should understand it discusses a prohibited review-bypass scenario as test material, not as an operational instruction or tool capability.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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 (1)

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
The security question is whether a reviewer recognizes the unjustified increase
in authority assigned to contextual data. This specimen contains no imperative
injection payload, impersonated system instruction, persistent rule file,
hidden characters, or operational method for disabling a security control.

## Static test vector

Static analysis

No suspicious patterns detected.