ClawHub
Back to skill

Security audit

Critical Article Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown writing-style skill with no executable code or hidden system access; the scanner concerns appear to be false positives.

Before installing, understand that this skill is meant to shape writing style and may produce pointed criticism. Use it with your own evidence and review outputs for accuracy, sourcing, and fair phrasing, especially around companies or people.

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
  • 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
Findings (2)

Self-Modification

High
Category
Rogue Agent
Content
1. Share examples of articles you want to emulate
2. Point out specific phrases or techniques you want more/less of
3. Reference the checklists to identify tone issues
4. Update SKILL.md with clarifications
5. Reload the skill in Claude Desktop

---
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Memory Manipulation

High
Category
Memory Poisoning
Content
```
CLAIM:
[Clear statement of position]

EVIDENCE LAYER 1:
[Data point with source]
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Static analysis

No suspicious patterns detected.