Back to skill

Security audit

Youtube Lite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed YouTube/TranscriptAPI helper with expected API-key use and no hidden code or destructive behavior.

Before installing, confirm you are comfortable giving TranscriptAPI.com your API key and YouTube queries, and avoid saving the key to local config on shared machines unless you accept plaintext config and backup exposure.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description says to use the skill whenever you need 'comprehensive YouTube access' or 'the full suite of YouTube data endpoints,' which is very broad and lacks clear activation boundaries. It does not provide specific trigger phrases, scope limits, or exclusion examples, increasing the risk of unintended invocation in many ordinary YouTube-related contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The text 'Everything in one skill' is an ambiguous capability claim rather than a specific activation guideline. Because it lacks constraints or negative examples, an agent could over-select this skill for general YouTube-related requests beyond its intended API-backed operations.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
86% confidence
Finding

The skill explicitly instructs persisting an API key into a local config file under ~/.openclaw/openclaw.json, creating longer-lived credential storage outside the immediate session. Persistent storage increases exposure if the host is shared, backups are accessible, file permissions are weak, or other tools later read and misuse the saved secret.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
You MUST have a `$TRANSCRIPT_API_KEY` environment variable set.

If you don't have tell the user to create a free account at transcriptapi.com: [transcriptapi.com/signup](https://transcriptapi.com/signup) → Dashboard → API Keys.

If you have the key, See **File Writes** below for details. Existing file is backed up before modification.

Static analysis

No suspicious patterns detected.