Back to skill

Security audit

MC Server Plugin Security

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Minecraft plugin security knowledge base, but it instructs agents to persistently modify the installed skill from later conversations without clear prior user approval.

Install only if you are comfortable with the skill being treated as a mutable knowledge base. Prefer making its installed directory read-only during normal use, or require reviewable patches and explicit approval before any SKILL.md update.

Vulnerability Patterns
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • 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
Findings (1)

T02 · Agent Memory Poisoning

Warning
Location
SKILL.md:17
Finding

Persistent Skill Modification Using Conversation-Derived Content

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 17-31
Vulnerability Type: Persistent agent-memory poisoning through mandatory self-modification
Risk Level: Medium

Vulnerable Instruction Snippet

The following is an English translation of the complete affected instruction block:

markdown
**This Skill is a living document and must continuously accumulate experience
and corrections. It is not a one-time artifact.**

Update triggers:
- New problems, observations, or countermeasures encountered while investigating
  or repairing Minecraft plugin vulnerabilities or security issues
- New plugin-security requirements provided by users that produce new best practices
- Findings from server testing or official-release verification that static analysis
  alone could not identify

Update rules:
1. Append information to the appropriate section and update the quick-index table.
2. Record each entry as: problem | symptom/error | countermeasure, including its source.
3. Update the version number and updated date.
4. After every use of this Skill, if the conversation contains experience worth
   retaining, proactively add it and tell the user that the Skill was updated.
5. Perform the mandatory sanitization review before updating.
6. Perform the mandatory post-modification review immediately after updating.
7. Every modification must update the version, date, and changelog.

Technical Analysis

The Skill instructs an agent to persist information obtained from later conversations directly into SKILL.md. Because this file contains instructions that govern future agent sessions, modifying it is not equivalent to writing an isolated incident report or temporary note. Newly inserted material can become trusted operational guidance whenever the Skill is loaded again.

The included sanitization requirements address identifiable information such as IP addresses, account names, paths, and token ...[truncated 2921 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove the requirement to automatically modify SKILL.md after normal conversations.
  2. Require explicit, informed user approval before generating or applying any persistent update.
  3. Produce a reviewable patch instead of directly editing the installed Skill.
  4. Store incident notes in a separate, non-instructional data file so that untrusted observations cannot automatically become agent directives.
  5. Require independent verification against authenticated upstream releases, official advisories, reproducible tests, or multiple trusted sources.
  6. Record provenance for every retained claim, including source URL, retrieval date, affected versions, verification method, and reviewer.
  7. Reject update requests originating solely from untrusted conversation content when authoritative corroboration is unavailable.
  8. Protect the installed Skill directory with read-only permissions during ordinary use and enable writes only through a controlled maintenance workflow.
  9. Use version control, signed commits, mandatory code review, and rollback procedures for all persistent changes.
  10. Validate proposed updates for unsafe commands, untrusted download locations, instruction hijacking, and contradictions with existing safety requirements in addition to performing privacy sanitization.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README says the skill is automatically triggered by broad keywords related to Minecraft plugin security, but it does not clearly bound when the skill should or should not activate. In an agent setting, overbroad triggers can cause the skill to fire in unrelated conversations, injecting security guidance or operational instructions unexpectedly and increasing prompt-surface and misapplication risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description is entirely in Chinese and presents the skill as a Chinese-language knowledge base with no indication that users may choose another language. The policy for this audit flags language/locale constraints when a skill forces a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 300)May include surrounding context.

md
jar tf "<插件.jar>" | grep -iE "backdoor|hack|exploit|shell|payload|webshell|forceop"

# 官方仓库最新 release 与日期
curl -s "https://api.github.com/repos/<owner>/<repo>/releases?per_page=8" | grep -E '"tag_name"|"published_at"'

# 官方某个 commit 的日期(核对修复是否早于手里的 jar)
curl -s "https://api.github.com/repos/<owner>/<repo>/commits/<hash>" | grep '"date"'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 303)May include surrounding context.

md
jar tf "<插件.jar>" | grep -iE "backdoor|hack|exploit|shell|payload|webshell|forceop"

# 官方仓库最新 release 与日期
curl -s "https://api.github.com/repos/<owner>/<repo>/releases?per_page=8" | grep -E '"tag_name"|"published_at"'

# 官方某个 commit 的日期(核对修复是否早于手里的 jar)
curl -s "https://api.github.com/repos/<owner>/<repo>/commits/<hash>" | grep '"date"'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The README presents usage through fixed Chinese and English sections and does not state that users may choose another language or that the skill is restricted to these locales for a documented reason. Under the policy rule, fixed language behavior without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.