ClawHub
Back to skill

Security audit

SPF Test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad coding-workflow guide with disclosed memory and TDD themes, but the submitted package contains only a descriptive README-style skill file.

Before relying on it, inspect the linked GitHub repository because the submitted package does not include the actual referenced workflow files. Treat its persistent-memory and subagent features as potentially broad logging or delegation behavior when used from the external project.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill advertises itself for 'any coding project' and a wide range of common development tasks, which makes it likely to be invoked in many contexts without clear scope limits. Broad activation increases the chance that downstream unsafe instructions, file operations, or workflow assumptions are applied where they are not appropriate, expanding the attack surface and encouraging over-trust in a powerful meta-skill.

Static analysis

No suspicious patterns detected.