ClawHub
Back to skill

Security audit

TikTok Data

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed Superagnt TikTok API helper, but it also points agents toward enabling broader Superagnt platform tools outside the advertised TikTok scope.

Install only if you intend to use Superagnt as a third-party TikTok data provider. Keep the API key in environment variables, avoid pasting live keys into prompts or logs, and do not enable non-TikTok MCP tool families unless you specifically want Superagnt workspace files, databases, webhooks, queues, or enrichment tools available to the agent.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill instructs the agent to use a bearer API key in outbound requests but does not clearly warn that the key and user-supplied query data will be transmitted to a third-party service. In an agent context, missing privacy and data-handling warnings can lead users to unknowingly route sensitive inputs or secrets to an external API.

External Transmission

Medium
Category
Data Exfiltration
Content
One call proves the key, the credit balance, and this source end to end:

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
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
One call proves the key, the credit balance, and this source end to end:

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
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
One call proves the key, the credit balance, and this source end to end:

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
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
## Example

```bash
curl -X GET 'https://api.superagnt.com/v1/data/tiktok' \
  -H 'X-API-Key: your_api_key_here' \
  -H 'Content-Type: application/json'
```
Confidence
80% confidence
Finding
The example uses an X-API-Key header with a placeholder key, which conflicts with earlier Bearer-token guidance and may encourage less controlled credential handling. In practice, inconsistent examples can cause users to expose keys in copied commands, shell history, shared screenshots, or debugging output while attempting to make the skill work.

Intent-Code Divergence

Low
Confidence
93% confidence
Finding
The skill states that authentication uses an Authorization Bearer token, but the later example uses an X-API-Key header. Inconsistent auth guidance can cause agents or users to send credentials incorrectly, increasing the chance of failed requests, insecure workarounds, or accidental credential leakage into logs and prompts while troubleshooting.

Description-Behavior Mismatch

Low
Confidence
95% confidence
Finding
The manifest description scopes the skill to TikTok videos, creators, sounds, and trend data as structured JSON. However, these lines advertise discovery of unrelated platform features such as workspace databases, files, webhooks, queues, and people/company enrichment, which goes beyond the stated TikTok-data purpose.

Static analysis

No suspicious patterns detected.