facebook-data

• Outcome: Review
• Latest audit: Sep 20, 2026 · 11:47 AM UTC
• Version: 2.0.5

Overview

The skill is mostly a disclosed Superagnt Facebook data API wrapper, but it gives conflicting information about whether scraping is involved and lacks clear data-handling guidance for third-party queries.

Review this carefully before installing if your use case has privacy, compliance, or platform-terms constraints. Treat Facebook links, IDs, search terms, and marketplace or people queries as data sent to Superagnt, and do not use it for sensitive investigations unless you are comfortable with Superagnt's data handling and the unresolved scraping disclosure conflict.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Description-Behavior Mismatch

High

• Confidence: 98% confidence
• Finding: The manifest claims the skill works 'without scraping,' yet the documentation later describes page sections 'to scrape' and repeatedly presents functionality consistent with scraping Facebook content via a third-party service. This contradiction is dangerous because it can bypass user scrutiny, compliance checks, or procurement decisions that would differ for scraping versus sanctioned API access.

Intent-Code Divergence

High

• Confidence: 99% confidence
• Finding: The inline parameter documentation explicitly says a page section is 'to scrape,' directly contradicting the manifest's safety-relevant representation. In context, this strengthens evidence that the skill obscures its actual data acquisition method, which can cause operators to unknowingly authorize scraping workflows with legal, privacy, or platform-policy consequences.

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The manifest claims the skill works 'without scraping,' yet the documentation later describes page sections 'to scrape' and repeatedly presents functionality consistent with scraping Facebook content via a third-party service. This contradiction is dangerous because it can bypass user scrutiny, compliance checks, or procurement decisions that would differ for scraping versus sanctioned API access.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill instructs users to send Facebook links, IDs, search queries, and related identifiers to a third-party API, but provides no privacy notice, retention statement, or data-handling boundaries. This omission is risky because operators may transmit sensitive research targets, user-generated content references, or internal investigation terms to an external processor without informed consent or governance review.

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

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.

Static analysis

No suspicious patterns detected.