ClawHub
Back to skill

Security audit

building-full-social-audit-for-brand

Security checks across malware telemetry and agentic risk

Overview

The skill appears intended for social-media auditing, but it overstates its multi-platform capability and handles an Apify credential in a risky way.

Review before installing. Treat this as a Twitter-focused Apify scraper skill unless the publisher adds real Instagram, TikTok, and YouTube steps. Only use it if you are comfortable sending brand handles and retrieving scraped results through Apify, and avoid command forms that put APIFY_TOKEN in URLs or logs.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Description-Behavior Mismatch

High
Confidence
98% confidence
Finding
The manifest promises a comprehensive multi-platform audit with per-platform metrics and a weighted brand health score across four named platforms. But the actual skill file defines Twitter-specific inputs, runs only the `apidojo~twitter-user-scraper`, and never provides concrete execution steps for Instagram, TikTok, or YouTube, so the described capability materially exceeds the documented implementation.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description lists several long-form trigger phrases such as 'do a social media audit for a brand' and 'build a full social media presence report' as activation conditions, but it does not define exclusions, required context, or negative examples. This can cause unintended invocation because these phrases are plausible in ordinary analysis requests and the skill does not clearly distinguish when it should or should not activate.

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The title and introductory documentation say this skill builds a full social audit for a brand using apidojo scrapers. However, the only executable instructions shown in Step 2, including CLI, MCP, and REST examples, all target `twitter-user-scraper`, which contradicts the stated full multi-platform intent rather than merely omitting detail.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs use of external scrapers and an API token but does not disclose that brand/account identifiers and resulting data will be transmitted to a third-party service. In agent settings, lack of transparency around external transmission and credential use can cause unreviewed sharing of user-supplied data and accidental misuse of environment-stored secrets.

External Transmission

Medium
Category
Data Exfiltration
Content
**REST API fallback:**
```bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~twitter-user-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"searchTerms": "@[BRAND_HANDLE]" (run per platform), "maxItems": 100}'
Confidence
94% confidence
Finding
This command performs external transmission to a third-party endpoint and places the APIFY token directly in the request URL. Putting secrets in URLs is risky because URLs can be logged by shells, proxies, monitoring systems, browser history, and server access logs, potentially exposing the credential while also sending user query data off-platform.

External Transmission

Medium
Category
Data Exfiltration
Content
Wait for `SUCCEEDED`. Fetch dataset:
```bash
curl "https://api.apify.com/v2/actor-runs/$RUN_ID/dataset/items?token=$APIFY_TOKEN"
```

### Step 3: Classify Results
Confidence
92% confidence
Finding
Fetching dataset items from the external API continues the third-party data flow and again embeds the APIFY token in the URL, compounding credential exposure risk. Returned datasets may also contain scraped content or identifiers that users may not expect to retrieve from an external store without a clear disclosure.

External Transmission

Medium
Category
Data Exfiltration
Content
Wait for `SUCCEEDED`. Fetch dataset:
```bash
curl "https://api.apify.com/v2/actor-runs/$RUN_ID/dataset/items?token=$APIFY_TOKEN"
```

### Step 3: Classify Results
Confidence
92% confidence
Finding
Fetching dataset items from the external API continues the third-party data flow and again embeds the APIFY token in the URL, compounding credential exposure risk. Returned datasets may also contain scraped content or identifiers that users may not expect to retrieve from an external store without a clear disclosure.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.