ClawHub
Back to skill

Security audit

Craftwork

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill provides disclosed software-engineering workflow guardrails and does not contain hidden execution, persistence, credential handling, or exfiltration behavior.

Install this if you want the agent to follow stricter engineering workflows. Be aware that some subskills encourage commits, pushes, merges, and subagent delegation as part of normal development, so keep your usual review and repository permission boundaries in place.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Philosophy

Agents are fast but sloppy. They skip tests, guess at fixes, claim "done" without checking, and agree with every review comment. These skills add guardrails — not to slow agents down, but to make their speed count.

Every skill follows the same pattern: **stop, verify, then act.**
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.

Vague Triggers

Medium
Confidence
91% confidence
Finding
This markdown file says 'Every non-trivial task needs a plan' without defining what counts as 'non-trivial' or providing boundaries or exclusions. That ambiguity can cause the skill to be invoked for many ordinary development requests where a detailed planning workflow may not be intended.

Static analysis

No suspicious patterns detected.