Back to skill

Security audit

geekflare

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly disclosed Geekflare web research and diagnostic tools, with routine privacy, credential, and installation considerations.

Queries, URLs, and extraction prompts go to Geekflare, so exclude confidential details and sensitive URL parameters. Protect the API key and key-bearing MCP URL, expect credit usage, and consider who can access hosted captures. If choosing local installation, pin a reviewed package version; install only the integration needed for your client.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The chunk's sole action is extension installation, rather than execution of the advertised Geekflare operations. Although the repository is related to Geekflare, installing an extension changes the local tool environment and is materially different from merely using the described web capabilities. The behavior of the downloaded extension cannot be established from this chunk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y @geekflare/mcp'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The local MCP setup uses npx -y @geekflare/mcp without a version pin, allowing a newly published package version to execute without an approval prompt. If the package or publisher account is compromised, malicious code could run with the agent process's permissions and access its API key and other accessible local data; the legitimate setup context does not eliminate this supply-chain risk.

Content

No source excerpt is available for this finding.

The research workflow sends search queries and target URLs to Geekflare without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

These workflow steps instruct the agent to submit queries and URLs to a third-party service, but the skill does not warn users that those inputs leave their environment. The public-content restriction does not address sensitive information contained in a user's research query or URL parameters.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 176)May include surrounding context.

When MCP tools are not available, the same features are served at https://api.geekflare.com. Every endpoint is a POST with a JSON body. The key goes in the x-api-key header, never in the URL or query string:

bash
curl -sS -X POST https://api.geekflare.com/dnsrecord \
  -H "x-api-key: $GEEKFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","types":["A","MX"]}'

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 176)May include surrounding context.

When MCP tools are not available, the same features are served at https://api.geekflare.com. Every endpoint is a POST with a JSON body. The key goes in the x-api-key header, never in the URL or query string:

bash
curl -sS -X POST https://api.geekflare.com/dnsrecord \
  -H "x-api-key: $GEEKFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","types":["A","MX"]}'

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:200