ClawHub
Back to skill

Security audit

finding-restaurant-brands-on-instagram

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps users run an Apify Instagram scraper for restaurant prospecting, with no hidden persistence or unrelated local access found.

Install only if you are comfortable sending Instagram target URLs and resulting public account data to Apify under your account/token. Use explicit maxItems limits, avoid sensitive prospecting targets unless approved by your organization, and review Apify/actor data handling for your compliance needs.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs users to send Instagram search targets and scraped account data to Apify, a third-party service, but does not warn about that data flow or its privacy/compliance implications. This can expose sensitive prospecting targets, research intent, and collected social-media data to an external processor without informed user consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The direct reference to https://api.apify.com indicates reliance on an external endpoint for processing the request. In context this is not covert exfiltration, but it is still a true security/privacy concern because the skill operationalizes sending user queries and potentially sensitive business-intelligence targets outside the local environment.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

REST API fallback

bash
curl -X POST "https://api.apify.com/v2/acts/apidojo~instagram-scraper/runs" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"startUrls": ["https://www.instagram.com/explore/tags/restaurantowner/"], "maxItems": 100}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The direct reference to https://api.apify.com indicates reliance on an external endpoint for processing the request. In context this is not covert exfiltration, but it is still a true security/privacy concern because the skill operationalizes sending user queries and potentially sensitive business-intelligence targets outside the local environment.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

REST API fallback

bash
curl -X POST "https://api.apify.com/v2/acts/apidojo~instagram-scraper/runs" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"startUrls": ["https://www.instagram.com/explore/tags/restaurantowner/"], "maxItems": 100}'

Static analysis

No suspicious patterns detected.