ClawHub
Back to skill

Security audit

Grant Budget Justification

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local grant budget justification generator with disclosed file output and no evidence of network access, persistence, credential access, or hidden behavior.

Before installing, understand that this is a draft-quality local script. Use it only with grant budget data you are comfortable processing locally, choose output paths carefully, and expect limited functionality because the documented JSON/CSV input options are not actually implemented in the bundled script.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill describes file output capability (--output, writing files to the workspace) and explicitly notes local script execution, but it does not declare any tool scope such as permissions or allowed-tools. This creates an authorization gap where the skill's actual file-write behavior is not constrained or transparently declared, increasing the risk of unintended or overly broad file modification if the implementation is permissive.

Content

No source excerpt is available for this finding.