ClawHub
Back to skill

Security audit

admapix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AdMapix API assistant that uses a user-provided API key for ad and app analytics, with no evidence of hidden persistence, local data access, or destructive behavior.

Install only if you intend to send ad/app analytics queries to AdMapix using your own API key. Be aware that broad prompts about rankings, revenue, markets, or downloads may activate the skill and send the query terms to AdMapix.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (6)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
**Reuse data:** If the user asks follow-up questions about already-fetched data, analyze existing results first. Only make new API calls when needed.

## Output Guidelines

1. **Language consistency** — ALL output (headers, labels, insights, hints, errors, disclaimers) must match the user's detected language. See "Language Handling" section above.
2. **Route-appropriate output** — Don't force H5 links on analytical questions; don't dump tables for browsing
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest includes many broad trigger phrases such as generic market, ranking, analysis, and revenue terms in both Chinese and English. This can cause the skill to activate on ordinary user conversations unrelated to AdMapix, unintentionally routing user requests into this skill and increasing the chance that user queries are sent to the external API without clear intent.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# GET
curl -s "https://api.admapix.com/api/data/{endpoint}?{params}" \
  -H "X-API-Key: $SKILLBOSS_API_KEY"

# POST
Confidence
60% 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
# GET
curl -s "https://api.admapix.com/api/data/{endpoint}?{params}" \
  -H "X-API-Key: $SKILLBOSS_API_KEY"

# POST
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
# GET
curl -s "https://api.admapix.com/api/data/{endpoint}?{params}" \
  -H "X-API-Key: $SKILLBOSS_API_KEY"

# POST
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Low
Confidence
84% confidence
Finding
Defaulting uncertain requests to Creative Search weakens intent boundaries and biases the system toward external querying even when user intent is ambiguous. In practice, ambiguous prompts may be over-collected and transmitted to the ad intelligence backend, creating unnecessary data exposure and unintended skill execution.

Static analysis

No suspicious patterns detected.