ClawHub
Back to skill

Security audit

Google Shopping — FlashData

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Google Shopping data connector that sends user-chosen shopping queries to FlashData using an API key and paid credits.

Install only if you are comfortable giving FlashData your shopping queries, locale settings, and a FlashData API key. Set the key through protected environment configuration, review credit costs before running queries, and avoid resubmitting timed-out paid jobs automatically.

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 (4)

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 95)May include surrounding context.

md
## Connection and responses

For hosted MCP, connect `https://data.flashdata.dev/mcp` using Streamable HTTP and an `X-API-Key` header in your client's protected settings. Keep keys out of chat and committed files.

The CLI returns `{"ok":true,"tool":"google_shopping","result":...}`; read the data inside `result`. MCP clients expose the same data in the tool response. Check errors before processing results. For a free quote, call `get_pricing` with `{"source":"google_shopping","request_count":1}`; a quote does not run the data query.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The JSON sets "hl": "en", which forces English results. For all file types, hard-coding a language or locale without user opt-in or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This is a manifest/config file, so vague-trigger review applies. The gl and hl fields are described only as values to set 'when needed', without specifying the circumstances or constraints for using them, which leaves invocation behavior around locale selection underdefined.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.