ClawHub
Back to skill

Security audit

Performance Budget Enforcer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent performance-budget helper that reads build outputs and may create project budget files, with no evidence of hidden or malicious behavior.

Before installing, understand that using the budget and trend workflows can modify repository files and that the CI example can post a PR comment if wired into GitHub Actions. Review or confirm those changes like any other project configuration update.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
93% confidence
Finding
The skill explicitly instructs creating and later appending to repository files such as `.perfbudget.json` and `.perfbudget-history.json`, but it does not warn the user that executing the workflow will modify tracked project contents. In an agent context, silent file writes can create unintended commits, pollute CI state, or overwrite existing configuration/history, even though the purpose here appears operational rather than malicious.

Static analysis

No suspicious patterns detected.