ClawHub
Back to skill

Security audit

Context.dev

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Context.dev integration for public-web research and scraping, with expected third-party API use and no hidden local execution or persistence.

Install this only if you intend to use Context.dev for web and document processing. Treat submitted URLs, queries, uploaded documents, and extraction prompts as data sent to a third-party service, and review confirmations for monitors or batches because they may persist or spend service credits.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is extremely broad and explicitly says to trigger even when users do not mention Context.dev. That can cause over-invocation of a web-connected skill, increasing the chance that user prompts or sensitive context are sent to an external service without sufficiently specific user intent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

This skill instructs the agent to send data to an external MCP or REST endpoint using an API key. In a skill designed for web search and scraping, external transmission is expected, but it still creates a real data-exfiltration risk if user content, internal URLs, or sensitive prompts are forwarded without strict minimization and consent.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

https://mcp.context.dev/mcp

text

Otherwise call the REST API at `https://api.context.dev/v1` with `Authorization: Bearer <key>`.

## Choose the narrowest operation

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 66)May include surrounding context.

Basic request pattern:

bash
curl -sS "https://api.context.dev/v1/web/scrape/markdown?url=https%3A%2F%2Fexample.com" \
  -H "Authorization: Bearer $CONTEXT_API_KEY"

Static analysis

No suspicious patterns detected.