Back to skill

Security audit

Speech is Cheap Transcribe

Security checks for vulnerabilities and agentic risk

Overview

The skill sends requested recordings for transcription and offers optional wallet payments with a user-approved spending limit.

Install if you intend to send recordings to Speech is Cheap. Its [security page](https://speechischeap.com/company/security/) says ordinary transcripts remain available indefinitely; use --private for sensitive recordings. For wallet mode, use a trusted signer, approve each spending ceiling, and keep payment state files confidential. Dependency code, actual retention, settlement, and refunds were not independently verified.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · scripts/x402.mjs (reported line 184)May include surrounding context.

js
if (response.status === 402 && response.headers.get('PAYMENT-REQUIRED')) {
    // A fresh challenge means the service rejected this proof without taking payment.
    const { error } = decodePaymentRequiredHeader(response.headers.get('PAYMENT-REQUIRED'));
    delete state.paymentHeaders;
    await saveState(path, state);
    throw new UsageError(`Payment was declined (${error || 'no reason given'}); no payment was taken. Fix the cause, then resume to sign a new quote.`);
  }

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · scripts/x402.mjs (reported line 192)May include surrounding context.

js
// The service never submits a declined authorization again.
    const { success, errorReason } = decodePaymentResponseHeader(response.headers.get('PAYMENT-RESPONSE'));
    if (success === false) {
      delete state.paymentHeaders;
      await saveState(path, state);
      throw new UsageError(`Settlement was declined (${errorReason || 'no reason given'}); no payment was taken. Fix the cause, then resume to sign a new quote.`);
    }

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/asr.sh (reported line 11)May include surrounding context.

sh
exec node "$(dirname "${BASH_SOURCE[0]}")/x402.mjs" "$@"
fi

API_BASE="https://api.speechischeap.com/v2"
UPLOAD_BASE="https://upload.speechischeap.com/v2"

# 1. Check for API Key

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 · scripts/asr.sh (reported line 81)May include surrounding context.

sh
}
EOF
)
            curl -s -X POST "$API_BASE/jobs/" \
                -H "Authorization: Bearer $SIC_API_KEY" \
                -H "Content-Type: application/json" \
                -d "$JSON_DATA"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 24)May include surrounding context.

md
description: Existing wallet module path for new x402 purchases and cancellation.
      - name: SIC_X402_API_BASE
        required: false
        description: Optional x402 API base override; unset uses https://api.speechischeap.com/v2.
---

# Speech is Cheap ASR

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · scripts/x402.mjs (reported line 14)May include surrounding context.

js
const NETWORK = 'eip155:8453';
const USDC = '0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913';
const DEFAULT_API = 'https://api.speechischeap.com/v2';
// Payment can be confirmed in the background, which starts the 300-second upload window.
const PENDING_UPLOAD_INTERVAL_MS = 30_000;
const PENDING_UPLOAD_REPLAYS = 20;