Back to skill

Security audit

Expert Insist

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only advice style skill with broad activation, but it does not request sensitive access, run code, persist services, or handle credentials.

Install this if you want advice answers to be more opinionated and self-challenging. Be aware that it may activate on many recommendation or planning questions, so users who prefer brief neutral answers may want narrower trigger wording.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares automatic activation for broad, common phrases such as 'analyze this', 'recommend', and general strategy/planning questions. In an agent framework, this can cause frequent unintended prompt injection of the skill's behavioral instructions into ordinary conversations, expanding its influence beyond the intended niche and potentially interfering with higher-priority safety or task-routing logic.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 71)May include surrounding context.

bash
mkdir -p skills/expert-insist
# Copy SKILL.md to skills/expert-insist/SKILL.md

The skill auto-triggers on opinion-based queries. No configuration needed.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire natural-language instruction set is written as Chinese-only operational guidance, with no indication that the skill adapts to the user's preferred language or that Chinese is a required regional constraint. Under the policy, a language-specific behavior without user opt-in or documented justification is a locale/language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill auto-triggers on a very broad set of common advice-seeking phrases, which makes it likely to activate in many ordinary conversations where the user did not explicitly request this behavior. Over-broad activation can hijack routing, override more appropriate skills, and cause the agent to apply opinionated multi-step reasoning in contexts where concise factual or neutral handling would be safer.

Content

No source excerpt is available for this finding.