YouTube Data API - Search, Videos, Comments, Transcripts, Channels

• Outcome: Pass
• Latest audit: Oct 11, 2026 · 10:53 PM UTC
• Version: 1.0.4

Overview

This skill is a straightforward YouTube data connector that sends user-requested YouTube queries to Scavio's documented API using a required API key.

Install this only if you are comfortable using Scavio as an intermediary for YouTube lookups and managing a SCAVIO_API_KEY. Avoid putting the API key in source control, and confirm costs before large pagination, transcript, stream, or bulk channel requests.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

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 · SKILL.md (reported line 191)May include surrounding context.

md

HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1. Search — use "search" field, not "query"
search = requests.post(f"{BASE}/api/v1/youtube/search", headers=HEADERS,
    json={"search": "langchain tutorial", "type": "video", "sort_by": "view_count"}).json()

video_id = search["data"]["results"][0]["video_id"]

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 · SKILL.md (reported line 197)May include surrounding context.

md

video_id = search["data"]["results"][0]["video_id"]

# 2. Full video metadata (captions list included)
video = requests.post(f"{BASE}/api/v1/youtube/video", headers=HEADERS,
    json={"video_id": video_id}).json()

# 3. Transcript as plain text

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 · SKILL.md (reported line 201)May include surrounding context.

md

json={"video_id": video_id}).json()

# 3. Transcript as plain text
transcript = requests.post(f"{BASE}/api/v1/youtube/transcript", headers=HEADERS,
    json={"video_id": video_id, "language": "en", "format": "text"}).json()

# 4. Resolve a handle, then pull the channel's videos

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 · SKILL.md (reported line 205)May include surrounding context.

md

json={"video_id": video_id, "language": "en", "format": "text"}).json()

# 4. Resolve a handle, then pull the channel's videos
resolved = requests.post(f"{BASE}/api/v1/youtube/channel/resolve", headers=HEADERS,
    json={"channel": "@freecodecamp"}).json()
channel_id = resolved["data"]["channel_id"]

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 · SKILL.md (reported line 209)May include surrounding context.

json={"channel": "@freecodecamp"}).json() channel_id = resolved["data"]["channel_id"]

videos = requests.post(f"{BASE}/api/v1/youtube/channel/videos", headers=HEADERS, json={"channel_id": channel_id}).json()

text

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The documentation states language defaults to en for /suggestions and /transcript, and region defaults to US for /suggestions. This imposes a specific language/locale behavior by default, and the file does not indicate user choice, opt-in, or a region-specific justification.

Content

No source excerpt is available for this finding.