Back to skill

Security audit

laomeng-zhc-kb

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign, with one low-probability, purpose-aligned flag; confidence is medium because the review was partial.

The verdict is benign, but not a guarantee of safety. Skillspector's review was partial: some referenced paths could not be matched to bundled files, and the image was outside its static analysis coverage. Consider these limits when deciding whether to install.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

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 · references/知识库导航.md (reported line 112)May include surrounding context.

md
| `分发/ide/说明.md` | 0.2.6 |
| `分发/skill/laomeng-zhc-agent/LICENSE.txt` | 1.0 |
| `分发/skill/laomeng-zhc-agent/README.md` | 1.7 |
| `分发/skill/laomeng-zhc-agent/SKILL.md` | 1.0.11 |
| `分发/skill/laomeng-zhc-agent/references/LSP协议.md` | 2.0 |
| `分发/skill/laomeng-zhc-agent/references/快速参考.md` | ZHC-LANG-1.8 |
| `分发/skill/laomeng-zhc-agent/references/智能体工作流.md` | 0.2.4 |

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 · references/知识库导航.md (reported line 119)May include surrounding context.

md
| `分发/skill/laomeng-zhc-agent/references/桥报文协议.md` | 2.4 |
| `分发/skill/laomeng-zhc/LICENSE.txt` | 1.0 |
| `分发/skill/laomeng-zhc/README.md` | 1.0.11 |
| `分发/skill/laomeng-zhc/SKILL.md` | 1.0.11 |
| `分发/skill/laomeng-zhc/references/快速参考.md` | ZHC-LANG-1.8 |
| `分发/skillhub/laomeng-zhc-agent/LICENSE.txt` | 1.0 |
| `分发/skillhub/laomeng-zhc-agent/README.md` | 1.7 |