ClawHub
Back to skill

Security audit

X (Twitter) Data

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a Superagnt X data connector, but it needs review because its instructions can expand beyond X into broader Superagnt platform tools.

Install only if you intend to send X research data and submitted text to Superagnt. Keep the API key private, prefer the scoped X connector, and do not enable broader Superagnt MCP tool families such as workspace files, databases, webhooks, or queues unless you explicitly need and understand that expanded access.

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 (8)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill encourages social listening and research workflows without a clear privacy warning that user queries, handles, tweet IDs, and analyzed text will be transmitted to a third-party API. This omission increases the risk of users unknowingly sending sensitive research targets, internal investigation topics, or personal data off-platform.

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.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill is presented as an X/Twitter data integration, but its documented tool surface also exposes unrelated AI and translation endpoints. This broadens the effective capability scope beyond what a user would reasonably expect, increasing the chance that sensitive user-provided text is sent to third-party services under a misleadingly narrow description.

External Transmission

Medium
Category
Data Exfiltration
Content
## Example

```bash
curl -X GET 'https://api.superagnt.com/v1/data/x' \
  -H 'X-API-Key: your_api_key_here' \
  -H 'Content-Type: application/json'
```
Confidence
80% confidence
Finding
The example request uses an X-API-Key header that conflicts with the earlier Bearer-token authentication guidance. In addition to being confusing, examples with raw key headers can encourage insecure copy-paste practices and increase the chance of credential leakage through custom tooling, logs, or debugging middleware.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The document expands from a narrowly described X-data skill into broader Superagnt platform discovery and tool-enablement guidance. In an agent setting, this can facilitate capability creep, where a user authorizes what appears to be a single-source connector but is steered toward discovering or enabling unrelated higher-impact tools.

External Transmission

Medium
Category
Data Exfiltration
Content
is never charged without a human confirming in the dashboard.

```bash
curl https://api.superagnt.com/v1/platforms
```

## Links
Confidence
91% confidence
Finding
This outbound call is not limited to the advertised X-data functionality; it points to a platform-wide discovery endpoint immediately after instructions about enabling additional tool families. In context, it increases the risk that an agent or user expands privileges and data access beyond the skill’s declared scope.

Intent-Code Divergence

Low
Confidence
98% confidence
Finding
The authentication instructions say to use an Authorization Bearer header, while the later example uses X-API-Key. Contradictory credential handling guidance can cause users or agents to place secrets in the wrong header, leading to failed auth, accidental logging, or insecure wrapper code that retries with multiple credential formats.

Static analysis

No suspicious patterns detected.