ClawHub
Back to skill

Security audit

cut-as-code

Security checks for vulnerabilities and agentic risk

Overview

This skill is a video-editing workflow router whose instructions are coherent, disclosed, and scoped to explicit project state and selected video operations.

Install this if you want an entry-point router for Project Protocol video-editing work. Make sure the referenced video leaf skills are installed and review their behavior separately, because this skill delegates actual editing, rendering, and artifact creation to them.

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 (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.

md
Read the selected skill's complete `SKILL.md` and every required sub-skill before

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 110)May include surrounding context.

md
multi-operation run, enter one owner at a time; after its self-check, recover project
state and continue to the next frozen operation without reopening intake.

Do not ask the user to approve a route that is already unambiguous. User interaction
belongs only to missing inputs, genuine routing ambiguity, credentials, or the
editorial/review decisions required by the owning skill. Never substitute an Agent
decision for a required human decision unless the user explicitly delegates it.

Static analysis

No suspicious patterns detected.