ClawHub
Back to skill

Security audit

monitoring-instagram-brand-mentions

Security checks across malware telemetry and agentic risk

Overview

The skill is a straightforward Instagram brand-monitoring guide that uses Apify as disclosed, but users should handle exported social-media data carefully.

Install only if you are comfortable sending Instagram monitoring keywords, hashtags, and URLs to Apify and storing scraped post data locally. Keep CSV/JSON exports in access-controlled locations, limit collection to what you need, and follow applicable platform, privacy, and business policies.

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 (6)

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The manifest and documentation claim the skill tracks mentions and classifies them by sentiment and type, identifies top advocates and critics, and delivers a brand health report. In the provided file, those capabilities are described as workflow steps and heuristic notes, but there is no code implementing classification, scoring, filtering, or report generation—only scraper invocation examples and prose instructions.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly encourages saving scraped Instagram data to local CSV/JSON files without any retention, access control, or sensitivity warning. Even if the data is scraped from public sources, local exports can contain personal data or sensitive business monitoring information and may be exposed through weak workstation security, shared directories, or accidental redistribution.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The REST example sends search terms and monitoring inputs to a third-party service without clearly warning users that their queries and resulting processing will occur off-platform. This can expose commercially sensitive monitoring targets, campaign keywords, or regulated personal-data workflows to an external processor without informed consent or proper governance.

External Transmission

Medium
Category
Data Exfiltration
Content
**REST API fallback:**
```bash
curl -X POST   "https://api.apify.com/v2/acts/apidojo~instagram-scraper/runs?token=$APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{"keywords": ["#[brand]", "#[brand]review"], "maxItems": 100}'
```

Run for each hashtag cluster. Merge results and deduplicate by `postUrl`.
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
**REST API fallback:**
```bash
curl -X POST   "https://api.apify.com/v2/acts/apidojo~instagram-scraper/runs?token=$APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{"keywords": ["#[brand]", "#[brand]review"], "maxItems": 100}'
```

Run for each hashtag cluster. Merge results and deduplicate by `postUrl`.
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Intent-Code Divergence

Low
Confidence
83% confidence
Finding
The workflow says Step 2 is to run the scraper, while a later heading also names Step 2 as mention classification. This is not just incomplete documentation; it actively conflicts about the intended stage boundaries and can mislead users about what the skill actually performs automatically.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.