Back to skill

Security audit

PlateUp! Wiki Guide

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the two scanner alerts were judged expected for its purpose, and the artifact was fully inspected.

The scanners report a benign verdict with high confidence, and all 13 listed components were inspected. The alerts relate to wording and installation setup, but benign does not mean risk-free; consider whether you trust and want to install this skill.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/index.md (reported line 3)May include surrounding context.

md
# Reference Index

Records use English names or stable IDs as canonical identifiers. Follow the bilingual display rules in [SKILL.md](../SKILL.md) and use the glossary for translation status.

| User asks about | Read |
|---|---|

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.en.md (reported line 56)May include surrounding context.

From the root of your local checkout, copy SKILL.md and references/ into the default Hermes skill directory:

bash
mkdir -p ~/.hermes/skills/plateup-wiki-skill/references
cp SKILL.md ~/.hermes/skills/plateup-wiki-skill/
cp -R references/. ~/.hermes/skills/plateup-wiki-skill/references/
hermes skills list

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 56)May include surrounding context.

在当前本地仓库根目录运行以下命令,将 SKILL.md 和 references/ 复制到 Hermes 的默认技能目录:

bash
mkdir -p ~/.hermes/skills/plateup-wiki-skill/references
cp SKILL.md ~/.hermes/skills/plateup-wiki-skill/
cp -R references/. ~/.hermes/skills/plateup-wiki-skill/references/
hermes skills list