ClawHub
Back to skill

Security audit

discovering-brand-ambassadors-across-platforms

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Apify-based social media discovery workflow, but its documentation overstates multi-platform coverage while mostly showing Instagram-only execution.

Install only if you are comfortable using Apify for this workflow and providing an APIFY_TOKEN. Expect the current instructions to behave like an Instagram-focused scraper unless the publisher adds concrete TikTok and Twitter collection steps, and review outputs carefully because the cross-platform reach scoring is internally inconsistent.

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 (5)

Description-Behavior Mismatch

High
Confidence
98% confidence
Finding
The manifest promises discovery across three platforms and says the output includes per-platform handles and combined reach estimates. However, the workflow, examples, REST fallback, and actor invocation all exclusively use `apidojo~instagram-scraper`, with no documented or implemented TikTok/Twitter collection step, so the described multi-platform behavior is not supported by the file.

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 '{"searchTerms": ["#[brand]", "#[brand]ambassador", "#[brand]fam"], "maxItems": 100}'
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 '{"searchTerms": ["#[brand]", "#[brand]ambassador", "#[brand]fam"], "maxItems": 100}'
```
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
**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 '{"searchTerms": ["#[brand]", "#[brand]ambassador", "#[brand]fam"], "maxItems": 100}'
```
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

Medium
Confidence
78% confidence
Finding
The edge-case guidance explicitly says not to just sum audience sizes across platforms, yet the next scoring guidance computes a single combined reach from Instagram, TikTok, and Twitter follower counts using additive weighting. That is an active contradiction in the documented intent versus the described computation.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.