ClawHub
Back to skill

Security audit

Spec

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed spec-management skill that creates gated planning files and validates approvals, with clear stops around production, secrets, service restarts, and pushing.

Install this only if you want your agent to use a gated spec workflow that writes planning files, records approval hashes, and may later execute approved coding tasks. Review your repo overlay carefully because it defines the high-risk surfaces, deployment steps, and hard stops the skill will follow.

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 · README.md (reported line 48)May include surrounding context.

md
Archive only after that step has run (`closure: deployed` or `verified`).
- **Verify:** a `npm run` command must exist in `package.json`, or name a CI
  job that does.
- **Hard stops:** never push without confirmation; never mutate production
  data or secrets; never restart a shared local service.
- **At closure:** run whatever specialist review this repo defines for the
  surfaces you touched.

Static analysis

No suspicious patterns detected.