Back to skill

Security audit

SocQ Facebook Ad Library Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped SocQ integration for researching public Facebook Ad Library data, with disclosed API use and cost controls, but users should be aware of the unpinned CLI install path.

Install only if you intend to send your Facebook Ad Library queries, supplied page IDs or URLs, and SocQ API-authenticated requests to SocQ. Prefer a pinned or preinstalled socq CLI where possible, set credit limits on the API key, and review expected credit usage before large or multi-endpoint runs.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill declares use of npx/Node-installed tooling without pinning a specific version, which creates supply-chain risk because a future or compromised package release could be fetched and executed implicitly. In an agent skill context, this is more dangerous because installation/execution steps may be automated and happen in unattended environments.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The instruction to run npx @socq/cli fetches and executes the latest package version unless a version is pinned, exposing users to remote code execution through package compromise or unexpected upstream changes. Because this skill is specifically instructing agents how to execute the tool, the unpinned reference is actionable and therefore materially risky.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

md
value: "socq"
      description: "Hosted SocQ Facebook Ad Library data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=facebook-ad-library"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · agents/openai.yaml (reported line 11)May include surrounding context.

yaml
value: "socq"
      description: "Hosted SocQ Facebook Ad Library data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=facebook-ad-library"