Back to skill

Security audit

DataXAPI Pinterest

Security checks for vulnerabilities and agentic risk

Overview

The skill provides public Pinterest lookups through a disclosed paid service, with ordinary privacy and package-installation precautions.

DataXAPI receives your lookup terms and charges your prepaid balance. Keep private context out of discovery requests and set spending limits. Prefer REST or review and pin the CLI version before running npm/npx. This review covers the complete bundled instruction file; the external CLI and service implementations remain unverified.

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
  • 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)

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 27)May include surrounding context.

Call it three ways

MCP. Server https://api.dataxapi.com/mcp, header Authorization: Bearer <key>. Tools: find (with platform: "pinterest" it lists this platform's endpoints), describe (parameters and price), call, read_more (free), account (balance). Setting the server up: https://dataxapi.com/agents.md

json
{"capability":"pinterest.pins.search","query":"mid century living room","max_price":"0.002"}

MCP server referenced without pinned version: 'npx dataxapi'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The recommended npx dataxapi and npm install -g dataxapi commands do not pin a package version, allowing newly published package code to execute with the agent's permissions. A compromised release or dependency could access the API key and local files; this is a CLI supply-chain risk, not an unversioned MCP server as the finding's label suggests.

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 42)May include surrounding context.

REST:

bash
curl -G "https://api.dataxapi.com/v1/pinterest/pins/search" \
  --data-urlencode "query=mid century living room" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

Endpoint discovery sends the user's wording to DataXAPI without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The fallback discovery instruction directs the agent to send the user's words to DataXAPI without requiring minimization or screening for sensitive information. Although external Pinterest searches are expected for this skill, endpoint discovery could unnecessarily disclose private context or identifiers when a generic capability description would suffice.

Content

No source excerpt is available for this finding.