ClawHub
Back to skill

Security audit

gladia-documentation-auto

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Gladia speech-to-text skill that clearly describes sending audio to Gladia APIs, with no hidden execution or persistence found.

Install this if you want Gladia transcription reference material. Before using it on real audio, confirm you have consent to send the audio/video to Gladia, protect the API key, avoid hardcoding credentials in client code, and configure zero data retention when privacy or compliance requires it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly markets itself as a general-purpose fallback when other specialized skills do not match, which can cause it to be invoked in cases where the user did not clearly intend to send audio, transcripts, or related metadata to Gladia. In a security-sensitive agent ecosystem, broad fallback routing increases the chance of unintended external data disclosure and weakens least-privilege behavior.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 6)May include surrounding context.

md
description: Comprehensive Gladia speech-to-text reference auto-synced from docs.gladia.io. Use as a general-purpose fallback when other specialized skills don't match, or when the user needs a broad overview of Gladia capabilities, endpoints, decision guidance, or workflows. Always prefer the official SDK; fall back to raw REST/WebSocket only when SDK cannot satisfy the requirement.
license: MIT
metadata:
  source: https://docs.gladia.io/.well-known/agent-skills/gladia/skill.md
  digest: sha256:fce0f1bdb678fca35d434a7f9f589187478d079847f0b9fcd6b846c032d1365c
  synced: "2026-10-02"
---

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 293)May include surrounding context.

md
description: Comprehensive Gladia speech-to-text reference auto-synced from docs.gladia.io. Use as a general-purpose fallback when other specialized skills don't match, or when the user needs a broad overview of Gladia capabilities, endpoints, decision guidance, or workflows. Always prefer the official SDK; fall back to raw REST/WebSocket only when SDK cannot satisfy the requirement.
license: MIT
metadata:
  source: https://docs.gladia.io/.well-known/agent-skills/gladia/skill.md
  digest: sha256:fce0f1bdb678fca35d434a7f9f589187478d079847f0b9fcd6b846c032d1365c
  synced: "2026-10-02"
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill describes uploading audio/video, extracting transcripts, and notes that data is retained by default, but it does not foreground a clear privacy warning at the point of use. Users or downstream agents may therefore transmit sensitive conversations, PII, or regulated audio without informed consent or appropriate safeguards.

Content

No source excerpt is available for this finding.

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 72)May include surrounding context.

export GLADIA_API_KEY=your_key

Or pass per request

curl -H "x-gladia-key: your_key" https://api.gladia.io/v2/pre-recorded

text

### Pre-recorded transcription (SDK)

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 211)May include surrounding context.

export GLADIA_API_KEY=your_key

Or pass per request

curl -H "x-gladia-key: your_key" https://api.gladia.io/v2/pre-recorded

text

### Pre-recorded transcription (SDK)

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 211)May include surrounding context.

  1. Initialize session (backend):
    javascript
    const response = await fetch("https://api.gladia.io/v2/live", {
  method: "POST",
  headers: { "x-gladia-key": "YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({

Static analysis

No suspicious patterns detected.