ClawHub
Back to skill

Security audit

SocQ Rednote Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent SocQ integration for public Rednote research, with expected network/API-key use and no evidence of hidden or destructive behavior.

Install only if you are comfortable sending Rednote research queries and returned public-data results to SocQ using your SOCQ_API_KEY. Prefer a pinned or preinstalled socq CLI over unpinned npx for stronger supply-chain control, and review costs before large or multi-endpoint runs.

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 (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.

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 74)May include surrounding context.

md
## Execution

1. Prefer an already configured SocQ MCP server at `https://api.socq.ai/mcp?platforms=rednote`; use the typed tool listed in [platform.md](references/platform.md), or compact `socq_execute` when needed.
2. If MCP is unavailable, use `socq` or `npx @socq/cli`. Use REST only as the final fallback.
3. Read [authentication.md](references/authentication.md), keep `SOCQ_API_KEY` in the environment, and never put it in prompts, URLs, committed files, or retained commands.
4. Read [billing.md](references/billing.md), report the expected cost, and obtain confirmation before a paid large-volume or multi-endpoint run.

Rp1

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The skill instructs use of npx @socq/cli without pinning a specific version, which can fetch and execute whatever package version is current at runtime. That creates a supply-chain risk: a compromised upstream package, malicious release, or breaking change could result in arbitrary code execution in the agent environment, potentially exposing SOCQ_API_KEY or altering research outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest declares a network-backed MCP tool that can send user research requests to an external SocQ service, but the user-facing metadata does not clearly disclose that external transmission will occur. This creates a transparency and consent gap: users or downstream agents may assume the skill operates locally when their prompts and collected data are actually sent to a third-party endpoint.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The skill is configured to communicate with an external HTTPS endpoint (api.socq.ai), which means user prompts, research targets, and retrieved data may leave the local trust boundary. Even if the endpoint is legitimate, this is dangerous when not clearly disclosed or constrained, because sensitive queries, identifiers, or investigative context could be transmitted to a third party.

Content

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

yaml
value: "socq"
      description: "Hosted SocQ Rednote data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=rednote"

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