ClawHub
Back to skill

Security audit

Skill Progressive Disclosure Design

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent advisory skill for organizing skill files, with broad but disclosed editing/evaluation tools and no hidden execution, credential access, or exfiltration behavior.

Install this as an advisory skill for skill authors. Expect it to read and potentially edit skill files when you ask for refactoring, and to use subagents for eval-style architecture checks; review its broad trigger wording if you want to reduce over-invocation.

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
93% confidence
Finding
The description says to trigger when the user "expresses any uncertainty about where to put content within a skill," which is an ambiguous and expansive activation condition for a markdown skill file. This lacks clear boundaries or negative examples, increasing the chance of unintended invocation on broadly phrased skill-design questions.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description instructs use "whenever creating a new Claude skill" and during general refactoring, which is broader than the specific topic of progressive disclosure design. Because many routine skill-authoring conversations could match this wording, the trigger scope is not sufficiently constrained to the specialized decision this skill is meant to address.

Vague Triggers

Low
Confidence
82% confidence
Finding
This JSON file is a manifest-type file, so vague-trigger checks apply. The sample pointer 'For advanced scenarios, see references/advanced.md for more information.' uses vague activation language like 'advanced scenarios' and 'for more information' with no observable condition, which could encourage ambiguous skill loading behavior.

Static analysis

No suspicious patterns detected.