ClawHub
Back to skill

Security audit

Send SMS text and bulk messages via TelTel.io API

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward TelTel SMS-sending skill with no hidden execution or persistence, but using it sends recipient details and messages to TelTel and may incur charges.

Install only if you intend to let an agent send real SMS messages through your TelTel account. Use dry-run first, keep TELTEL_API_KEY private, verify TELTEL_BASE_URL is trusted, and avoid sending sensitive message content or bulk messages without explicit user approval because charges and privacy exposure are expected.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The skill description claims delivery report support and bulk SMS functionality, but the documentation only clearly describes single-send and a bulk script, while the finding indicates some declared behaviors are not implemented. This mismatch can mislead users and agents into assuming features or controls exist when they do not, which is a security-relevant integrity problem for automation workflows.

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documents and enables use of environment variables and outbound network access to a third-party SMS API, but it does not declare any explicit tool scope or allowed-tools restrictions. In an agent environment, missing scope declarations weakens containment and makes it easier for the skill to be invoked with broader capabilities than are necessary.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs users to send real SMS messages through an external provider but does not warn that phone numbers, sender IDs, message bodies, and possibly callback URLs will be transmitted to a third party and may incur charges. In practice, this omission increases the likelihood of accidental disclosure of personal data or unintended spending.

External Transmission

Medium
Category
Data Exfiltration
Content
*   node send_sms_bulk.js --to "+3712..., +3712..." --message "Hi" --from "37163030348" [--callback "https://..."] [--apikey "..."] [--dry-run]
 */

const BASE_URL = process.env.TELTEL_BASE_URL || 'https://api.teltel.io/v2';

function parseArgs(argv) {
  const out = {};
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
*   node send_sms_bulk.js --to "+3712..., +3712..." --message "Hi" --from "37163030348" [--callback "https://..."] [--apikey "..."] [--dry-run]
 */

const BASE_URL = process.env.TELTEL_BASE_URL || 'https://api.teltel.io/v2';

function parseArgs(argv) {
  const out = {};
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
*   node send_sms_bulk.js --to "+3712..., +3712..." --message "Hi" --from "37163030348" [--callback "https://..."] [--apikey "..."] [--dry-run]
 */

const BASE_URL = process.env.TELTEL_BASE_URL || 'https://api.teltel.io/v2';

function parseArgs(argv) {
  const out = {};
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
*   node send_sms_bulk.js --to "+3712..., +3712..." --message "Hi" --from "37163030348" [--callback "https://..."] [--apikey "..."] [--dry-run]
 */

const BASE_URL = process.env.TELTEL_BASE_URL || 'https://api.teltel.io/v2';

function parseArgs(argv) {
  const out = {};
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/send_sms_bulk.js:9

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/send_sms.js:13