ClawHub
Back to skill

Security audit

think-like-fable

Security checks for vulnerabilities and agentic risk

Overview

This skill is a reasoning-style guide with broad activation wording, but it does not request privileged access, run code, persist data, or perform hidden actions.

Install this if you want the agent to use a more rigorous reasoning style on complex or high-stakes tasks. Be aware that common wording like 'are you sure?' or 'double-check that' may activate it even when you did not name the skill explicitly.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes broad phrases like 'be rigorous', 'think hard about this', 'reason carefully', and 'double-check that', which are common in normal conversations and can cause the skill to activate when the user did not explicitly request it. Because this skill changes the assistant's operating behavior across many high-stakes contexts, unintended activation can alter response style, increase hidden instruction precedence, and create prompt-routing ambiguity that other prompts or attackers may exploit.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'When to use this skill' section repeats the same ambiguous activation conditions and extends them to broad categories like security judgment, architecture calls, and any prompt from another skill or agent. This compounds the risk of over-broad routing: other prompts can indirectly cause activation, and normal user phrasing may unexpectedly load the skill, making behavior less predictable and easier to manipulate through prompt wording.

Content

No source excerpt is available for this finding.