Back to skill

Security audit

Systematic Debug

Security checks for vulnerabilities and agentic risk

Overview

This is a simple debugging-method skill with cluttered unrelated reference text, but it does not request sensitive access, persistence, execution, or hidden authority.

This skill appears safe to install from a security standpoint, but users should expect some irrelevant Bilibili reference clutter and potentially broad activation around debugging terms. The publisher should remove unrelated learning-history entries and narrow or clarify triggers.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are overly broad and common, so the skill may activate during ordinary conversation about problems or debugging without the user explicitly requesting this methodology. Unintended activation can override better-suited skills, inject irrelevant instructions, and amplify the effect of the unrelated content present elsewhere in the file.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill file contains substantial unrelated Bilibili learning/history content, including jailbreak-related PS5 material, that does not support the stated debugging workflow. This increases prompt-surface area, can confuse downstream agents about the skill’s purpose, and may introduce unsafe or policy-relevant behavior through irrelevant embedded context.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

A section presented within the debugging skill includes entries unrelated to debugging methodology, including entertainment and jailbreak-adjacent material, which contradicts the document’s stated focus. In agent skill systems, such contradictory context can contaminate behavior selection or retrieval and cause the agent to surface irrelevant or unsafe guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file specifies activation scenarios partly in Chinese, which can imply a language-specific invocation policy. There is no accompanying note that users may invoke the skill in other languages or that the Chinese-only phrasing is intentional for a region-specific use case.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.