Back to skill

Security audit

Transcribe audio files via OpenRouter using audio-capable models

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it converts a chosen audio file and sends it to OpenRouter for transcription, with no hidden persistence or unrelated behavior found.

Install only if you are comfortable sending selected audio recordings to OpenRouter and the chosen model provider. Avoid using it for confidential, regulated, or private conversations unless that third-party processing is acceptable for your use case, and provide the API key through a normal environment variable rather than embedding secrets in shared files.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill clearly invokes shell-based scripts and external binaries (curl, ffmpeg, base64, jq) but does not declare corresponding permissions. This can weaken user review and policy enforcement because the capability to execute shell commands is present even though it is not explicitly surfaced in the skill declaration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation says it transcribes audio via OpenRouter, but it does not prominently warn users that uploaded audio content is transmitted to a third-party service for processing. Audio may contain sensitive conversations, PII, or confidential business information, so insufficient disclosure can lead to unintended data exfiltration and privacy/compliance issues.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script uploads the full audio content to OpenRouter for processing without any explicit user-facing notice, confirmation, or safeguard about third-party data disclosure. In a transcription skill, this transmission is expected for functionality, but it still creates a real privacy and compliance risk because users may unknowingly send sensitive recordings to an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The script sends audio-derived payload data and associated metadata to an external API endpoint. Although external transmission is intrinsic to this skill's purpose, it remains a true security/privacy concern because potentially sensitive voice content is exfiltrated to a third party and may be subject to logging, retention, or policy controls outside the user's environment.

Content

Scanner excerpt · scripts/transcribe.sh (reported line 108)May include surrounding context.

sh
}' > "$payload_file"

# Make API request
response=$(curl -sS "https://openrouter.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Title: $title" \

Static analysis

No suspicious patterns detected.