Back to skill

Security audit

DataXAPI Telegram

Security checks for vulnerabilities and agentic risk

Overview

The skill retrieves public Telegram data as described, with disclosed usage charges and manageable privacy and installation risks.

DataXAPI receives Telegram identifiers and fallback discovery wording, so exclude private context and secrets from queries. Use a spending-limited API key and cap pagination. Prefer REST/MCP or an audited, pinned CLI version. This review covers the bundled instructions; the external CLI and service implementation were not audited.

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: "telegram" 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":"telegram.channels.messages.list","username":"telegram","max_price":"0.002"}

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/telegram/channels/messages/list" \
  --data-urlencode "username=telegram" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The documented npx dataxapi and global installation commands do not specify a version, allowing execution of a changing npm release. A compromised release could execute code with the agent's privileges and access its API key or local files; this is a CLI supply-chain issue rather than an unpinned MCP server.

Content

No source excerpt is available for this finding.

The fallback discovery workflow sends the user's words to DataXAPI without disclosing that their query text will be shared.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to send the user's words to an external discovery service without requiring minimization or screening for sensitive content. Although using DataXAPI is central to the skill, endpoint discovery does not necessarily require the user's original wording, which could contain private context or credentials.

Content

No source excerpt is available for this finding.