Back to skill

Security audit

DataXAPI Transcripts

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a coherent, cost-limited workflow for retrieving video transcripts through DataXAPI, with ordinary dependency and privacy considerations.

Use a reviewed, pinned CLI version and a limited-budget API key. Your supplied video URLs go to DataXAPI, and retrieved transcripts are saved locally, so avoid confidential or token-bearing links. Check the planned maximum charge before execution. The scanner’s reference gaps were resolved, but the external CLI and service behavior remain outside this artifact review.

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 (2)

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

Both npx dataxapi and npm install -g dataxapi can retrieve and execute an unpinned package version, allowing a compromised future release to run with the agent's permissions and potentially access its API key or local files. The reference is to a CLI, not an MCP server, but the underlying dependency supply-chain risk remains valid; nothing in the supplied skill establishes that the package is malicious.

Content

No source excerpt is available for this finding.

The execution workflow sends user-provided video links to DataXAPI without an explicit third-party data-sharing warning.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs the agent to disclose the maximum cost and then execute a DataXAPI request containing the supplied video links. Although the service is named, the skill does not tell the user that their links will be transmitted to a third-party service; cost disclosure and source attribution do not explain this privacy implication.

Content

No source excerpt is available for this finding.