ClawHub
Back to skill

Security audit

Techwrite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain technical-writing workflow and does not request system access, execute code, or handle sensitive data.

This skill is appropriate for users who want structured help writing or editing technical documentation. As with any writing assistant, review final text for factual accuracy, legal-sensitive claims, and organization-specific style requirements before publishing.

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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 114)May include surrounding context.

md
- **Peer review** for technical accuracy; **non-expert** read for onboarding docs

**Exit condition:** Another reader can follow without asking clarifying questions—or questions are **FAQ’d**.

---