ClawHub
Back to skill

Security audit

Focus Guard

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only focus-management skill that asks the agent to track goals, decisions, and scope changes, without hidden execution or data access.

This skill is safe to install if you want stricter session focus. Expect it to add brief scope checks and decision logs during longer tasks; users who prefer open-ended exploration may find that behavior unnecessarily restrictive.

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)

Scope Creep

Low
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md
| Tangent | Flag it. Defer to after current goal is done. |
| Out of scope | Decline politely. Stay on track. |

The rule: **expand scope only by explicit decision, never by default.**

### Step 5: Progress Check-in
For sessions with 5+ steps, offer a brief check-in at natural breakpoints:

Static analysis

No suspicious patterns detected.