ClawHub
Back to skill

Security audit

Presentation Mastery

Security checks for vulnerabilities and agentic risk

Overview

This is a presentation-coaching skill with broad but purpose-aligned invocation examples and no executable code, persistence, credential access, or hidden data handling.

Install this if you want structured help creating or improving presentations. Be aware that common requests about decks or slides may activate it, so invoke it explicitly when you want presentation-specific coaching.

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 (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The README presents generic phrases like "Help me build a presentation about [topic]" and "Review my slide deck" as invocation language without any limiting context, exclusions, or trigger constraints. These are broad enough to match ordinary conversation and could cause unintended activation in systems that rely on natural-language routing.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrase at this line is broad enough to overlap with ordinary user requests, which can cause the skill to activate unintentionally outside a clearly scoped presentation-design context. In an agent environment, this increases the chance of prompt hijacking, unintended delegation, or execution of this skill when the user meant a general conversation rather than specialized workflow behavior.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The listed natural-language commands are ambiguous and loosely scoped, making reliable intent matching difficult and increasing accidental activation risk. Because many of these phrases are common requests that could arise in unrelated contexts, a competing or adversarial prompt could more easily route control into this skill unexpectedly, producing confusing or unsafe agent behavior.

Static analysis

No suspicious patterns detected.