Back to skill

Security audit

bug-pattern-diagnosis

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only debugging skill whose risky-looking commands are disclosed troubleshooting examples, not hidden automatic behavior.

Install only if you want a Chinese-language intermittent-bug diagnosis helper. Review generated advice before running any Kubernetes, EMQX, or curl commands, especially cluster leave/join steps, and confirm the target environment and faulty node first.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (11)

Privileged Kubernetes Workload

High
Category
Tool Misuse
Confidence
55% confidence
Finding

Code deploys a privileged Kubernetes workload (privileged container, hostPath mount, or host namespaces). This grants root on the node and is a node/cluster takeover vector.

Content

Scanner excerpt · experience/BUG03.md (reported line 391)May include surrounding context.

md
- StatefulSet:`cuav-base-emqx`(namespace `cuav-cloud`)
- Pod:`cuav-base-emqx-0` / `cuav-base-emqx-1` / `cuav-base-emqx-2`
- Service:`cuav-base-emqx`(普通 ClusterIP)+ `cuav-base-emqx-headless`(headless,按 pod 直连)
- 持久化:`hostPath: /opt/cloud/hostPath/emqx-ha/emqx-data`
- EMQX 版本:5.1.3
- Dashboard 端口:18083;MQTT 端口:1883

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description is written entirely in Chinese and the document consistently constrains the skill's interaction style to Chinese-language operation, but it does not offer the user a language choice or explain a justified region-specific requirement. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list ends with a broad condition: any description involving '交叉产生 / 间歇性 / 不确定性'. These phrases overlap with many ordinary debugging conversations and do not clearly define when this skill should not activate, making invocation boundaries ambiguous.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all instructions, diagnostics, and remediation guidance exclusively in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a locale/language policy issue unless the regional constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · experience/BUG01.md (reported line 171)May include surrounding context.

bash
# 连续打 100 次同一请求(替换 URL 和 token)
for i in $(seq 1 100); do
  curl -s -X POST "$URL" -H "Authorization: $TOKEN" -d "$BODY" \
    | jq -r '.errorCode' | head -1
done | sort | uniq -c

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The entire skill file is written in Chinese and does not indicate that the user may choose another language or that the skill is intentionally restricted to Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · experience/BUG03.md (reported line 223)May include surrounding context.

md
# 通过 headless service 直连每个 pod
for i in 0 1 2; do
  EMQX_HOST="cuav-base-emqx-$i.cuav-base-emqx-headless.cuav-cloud.svc.cluster.local"
  TOKEN=$(curl -sS -X POST http://${EMQX_HOST}:18083/api/v5/login \
    -H 'Content-Type: application/json' \
    -d '{"username":"admin","password":"<dashboard-pwd>"}' \
    | sed -E 's/.*"token":"([^"]+)".*/\1/')

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · experience/BUG03.md (reported line 228)May include surrounding context.

md
-d '{"username":"admin","password":"<dashboard-pwd>"}' \
    | sed -E 's/.*"token":"([^"]+)".*/\1/')
  echo "--- publish to emqx-$i ---"
  curl -sS -X POST "http://${EMQX_HOST}:18083/api/v5/publish" \
    -H "Authorization: Bearer $TOKEN" \
    -H 'Content-Type: application/json' \
    -d '{"topic":"<target-topic>","payload":"VEVTVA==","payload_encoding":"base64","qos":1,"retain":false}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document gives cluster repair commands (emqx_ctl cluster leave and cluster join) that alter cluster membership and can disrupt connected clients, but the warning is not prominent or immediate at the command point. In an agent skill, users may copy-paste remediation steps directly, so insufficient nearby caution increases the risk of accidental service interruption or mis-execution on the wrong node.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · experience/BUG03.md (reported line 418)May include surrounding context.

md
emqx_ctl broker metrics | grep -E 'dropped|received|publish'

# 客户端订阅清单
curl -H "Authorization: Bearer $TOKEN" \
  http://emqx:18083/api/v5/clients/<clientid>/subscriptions

# HTTP API publish(绕过 client,直接走 broker 内部路由)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is written entirely in Chinese and does not offer any language or locale choice to the user. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.