ClawHub
Back to skill

Security audit

Brief Master

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-brief drafting helper with clear review boundaries and no hidden execution, persistence, or data-handling behavior.

Review generated briefs before giving them to autonomous agents, especially if they include commands, schedules, external services, credentials, or changes to code or data.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The declared description says the skill produces execution briefs, which is a content-generation/planning function. The supplied code does not generate briefs or assist with agents, cron jobs, reviewers, researchers, or delegated coding tasks. Instead, it performs static validation of a skill repository's files and documentation. This is a materially different primary purpose, so the description does not accurately represent the code's behavior.

Vague Triggers

Medium
Confidence
93% confidence
Finding
Because this is a markdown file, vague-trigger checks apply. The usage example "Help me write a cron job prompt for overnight research" starts with the highly generic phrase "Help me," which commonly appears in ordinary conversation and could cause unintended invocation if used as an activation cue without additional constraints or exclusions.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Static analysis

No suspicious patterns detected.