Back to skill

Security audit

SocQ Pinterest Research

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent SocQ integration for public Pinterest research, with disclosed API-key use and external SocQ requests, but users should be mindful of credit usage and the unpinned CLI fallback.

Install only if you are comfortable sending public Pinterest queries, supplied URLs/usernames, and your SocQ-authenticated requests to SocQ. Use an API key with spending/rate limits, confirm large paid jobs before running them, and prefer a pinned or already-installed SocQ CLI over ad hoc npx execution.

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 permits use of npx to obtain tooling without pinning a specific version, which creates a supply-chain risk: a future malicious or compromised package release could be executed in the agent environment. Because this skill is intended to access an API key and perform networked actions, unpinned runtime package resolution is more dangerous than in a purely local/read-only skill.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

Using npx @socq/cli without an exact version allows whatever version is current at execution time to run, enabling accidental breakage or deliberate supply-chain compromise. In this skill, that tool may handle SOCQ_API_KEY and transmit requests externally, so compromise could expose secrets or alter outbound operations.

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 Pinterest data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=pinterest"

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 Pinterest data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=pinterest"