Back to skill

Security audit

ytapi-youtube-search

Security checks for vulnerabilities and agentic risk

Overview

The YouTube features fit the stated purpose, but setup needs review because it saves your API key across sessions without asking and uses temporary files without specified access protections.

Prefer an existing YTAPI connector when available. Before using API-key setup, choose where the key will be stored, limit its availability to the agent that needs it, and require private temporary files. Optional registration sends your email and verification code to YTAPI; searches and transcript requests use account credits.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/auth-setup.md (reported line 94)May include surrounding context.

md
2. Check it in the current session without printing it, for example
   `test -n "$YTAPI_API_KEY" && echo set`. If the session must be reloaded to
   see it, reload it or tell the user.
3. Delete the temporary files: `rm -f /tmp/ytapi-signup.json /tmp/ytapi-verify.json`.

The user can sign in at https://ytapi.dev/auth/login?utm_source=skill&utm_medium=auth-setup with the same email to
see usage, manage keys and buy credits.

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 18)May include surrounding context.

md
homepage: https://ytapi.dev
    requires:
      bins:
        - curl
    primaryEnv: YTAPI_API_KEY
    envVars:
      - name: YTAPI_API_KEY

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 52)May include surrounding context.

Search (1 credit per page)

bash
curl -s -G "https://api.ytapi.dev/v1/search" \
  --data-urlencode "q=QUERY" -d type=video -d limit=20 \
  -H "Authorization: Bearer $YTAPI_API_KEY"

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 75)May include surrounding context.

Then read the videos (1 credit each)

bash
curl -s "https://api.ytapi.dev/v1/transcripts?video_id=VIDEO_ID&format=text" \
  -H "Authorization: Bearer $YTAPI_API_KEY"

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 · references/auth-setup.md (reported line 37)May include surrounding context.

to request in one step.

bash
curl -s -X POST https://ytapi.dev/api/agent/signup \
  -H "Content-Type: application/json" \
  -d '{"email": "USER_EMAIL"}' \
  -o /tmp/ytapi-signup.json

The skill creates remote accounts, extending beyond its declared YouTube search and transcript-reading scope.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

The signup and verification requests submit the user's email and verification code to create a YTAPI account and obtain an API key. Although the workflow asks for user consent, remote account creation is an additional state-changing capability not described by the manifest, rather than simply authenticating search requests with an existing key.

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 · references/auth-setup.md (reported line 60)May include surrounding context.

bash
TOKEN=$(sed -n 's/.*"signup_token":"\([^"]*\)".*/\1/p' /tmp/ytapi-signup.json)
curl -s -X POST https://ytapi.dev/api/agent/verify \
  -H "Content-Type: application/json" \
  -d "{\"signup_token\": \"$TOKEN\", \"code\": \"CODE\"}" \
  -o /tmp/ytapi-verify.json

The workflow persists the API key across sessions without warning the user about persistent credential storage.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow mandates storing the key for future sessions without a user-facing disclosure or choice about persistence. Allowing shell profiles or general configuration files without requiring restrictive permissions or isolation can expose the credential to unrelated sessions, processes, or configuration backups.

Content

No source excerpt is available for this finding.