ClawHub
Back to skill

Security audit

SocQ Bluesky Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SocQ integration for researching public Bluesky data, with expected network/API-key use and no hidden destructive behavior found.

Install only if you are comfortable sending public Bluesky research targets, query terms, and task requests to SocQ under your SOCQ_API_KEY. Prefer a pinned or preinstalled SocQ CLI in controlled environments, set credit/rate limits on the API key, and avoid submitting secrets, private data, or regulated information.

SkillSpector

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 (5)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding
Using `npx @socq/cli` without a pinned version allows the latest package version to be fetched and executed at runtime. If the upstream package is compromised or a breaking change is introduced, the agent could run unreviewed code with access to the `SOCQ_API_KEY` and any other ambient privileges.

External Transmission

Medium
Category
Data Exfiltration
Content
value: "socq"
      description: "Hosted SocQ Bluesky data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=bluesky"
Confidence
88% confidence
Finding
The skill is explicitly configured to transmit data to an external endpoint at api.socq.ai via streamable HTTP. In this research context, external transmission is expected, but it still introduces data exposure, third-party trust, logging, and supply-chain risk if users submit sensitive prompts, identifiers, or investigation targets.

External Transmission

Medium
Category
Data Exfiltration
Content
value: "socq"
      description: "Hosted SocQ Bluesky data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=bluesky"
Confidence
88% confidence
Finding
The skill is explicitly configured to transmit data to an external endpoint at api.socq.ai via streamable HTTP. In this research context, external transmission is expected, but it still introduces data exposure, third-party trust, logging, and supply-chain risk if users submit sensitive prompts, identifiers, or investigation targets.

Missing User Warnings

Low
Confidence
94% confidence
Finding
The skill declares a hosted external MCP/HTTP dependency but gives no user-facing disclosure that prompts, query terms, and possibly returned data will be sent to a third-party service. This creates a real transparency and privacy issue because users and downstream agents may invoke the skill without understanding that data leaves the local environment.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:32