ClawHub
Back to skill

Security audit

Speech is Cheap Transcribe

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Speech is Cheap transcription wrapper that sends user-selected audio or audio URLs to the provider, with no hidden persistence or unrelated behavior found.

Install this only if you are comfortable sending selected audio files, audio URLs, transcription options, and optional webhook URLs to Speech is Cheap. Use --private for sensitive recordings and avoid submitting confidential internal URLs or audio unless the provider's privacy terms fit your needs.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly encourages uploading local audio files to a third-party endpoint and configuring arbitrary webhook callbacks, but it does not clearly disclose the data egress, privacy implications, or the sensitivity of audio/transcript content. In an agent setting, this can cause unreviewed transmission of local files or derived transcripts to external services, increasing the risk of privacy breaches, data leakage, and accidental exfiltration of sensitive information.

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 6)May include surrounding context.

sh
# Speech is Cheap (SIC) CLI Wrapper for OpenClaw
# Documentation: https://docs.speechischeap.com

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
89% confidence
Finding

This POST request transmits user-supplied audio source information and transcription options to an external API. While that is the intended function of the skill, it still constitutes a real security/privacy risk because sensitive speech content or internal-only URLs may be disclosed to a third party without any validation, warning, or restriction.

Content

Scanner excerpt · scripts/asr.sh (reported line 76)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"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script uploads local audio files and sends remote audio URLs to a third-party transcription service, but it provides no explicit warning, consent prompt, or data-classification guidance before transmitting potentially sensitive content. In an agent-skill context, this is risky because users may assume processing is local while the skill silently exfiltrates speech data and optional webhook destinations to an external provider.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.