ClawHub
Back to skill

Security audit

Explainer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ListenHub explainer-video generator that sends user-confirmed content to its video API and stores limited local preferences.

Install only if you are comfortable sending the topic and source text you provide to ListenHub/Marswave for generation. Avoid submitting secrets or private content unless that service is approved for your use, and review whether you want outputs saved locally under .listenhub/explainer or only shown inline.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill hardcodes user-facing configuration summary and confirmation text in Chinese, including the prompt at L074, even though the skill later supports both Chinese and English. This imposes a language choice on users before they have opted into a locale, which conflicts with the policy against forcing a specific language without user choice.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
   EPISODE_ID="<id-from-step-1>"
   for i in $(seq 1 30); do
     RESULT=$(curl -sS "https://api.marswave.ai/openapi/v1/storybook/episodes/$EPISODE_ID" \
       -H "Authorization: Bearer $LISTENHUB_API_KEY" 2>/dev/null)
     STATUS=$(echo "$RESULT" | tr -d '\000-\037\177' | jq -r '.data.processStatus // "pending"')
     case "$STATUS" in
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
   EPISODE_ID="<id-from-step-1>"
   for i in $(seq 1 30); do
     RESULT=$(curl -sS "https://api.marswave.ai/openapi/v1/storybook/episodes/$EPISODE_ID" \
       -H "Authorization: Bearer $LISTENHUB_API_KEY" 2>/dev/null)
     STATUS=$(echo "$RESULT" | tr -d '\000-\037\177' | jq -r '.data.processStatus // "pending"')
     case "$STATUS" in
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
   EPISODE_ID="<id-from-step-1>"
   for i in $(seq 1 30); do
     RESULT=$(curl -sS "https://api.marswave.ai/openapi/v1/storybook/episodes/$EPISODE_ID" \
       -H "Authorization: Bearer $LISTENHUB_API_KEY" 2>/dev/null)
     STATUS=$(echo "$RESULT" | tr -d '\000-\037\177' | jq -r '.data.processStatus // "pending"')
     case "$STATUS" in
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
5. Ask output → "Text + Video"

```bash
curl -sS -X POST "https://api.marswave.ai/openapi/v1/storybook/episodes" \
  -H "Authorization: Bearer $LISTENHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.