Back to skill

Security audit

Youtube Serp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed YouTube research helper that calls the AIsa API and does not show hidden persistence, destructive behavior, or unrelated data access.

Before installing, users should understand that YouTube queries and the AIsa API key are sent to AIsa's API. Treat the channel, rankings, and trends wording as SERP-derived analysis rather than dedicated YouTube channel or trends APIs.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The code generally aligns with the stated YouTube research and competitor-scouting purpose: it searches YouTube through the AIsa API, supports country/language parameters, returns video results, and includes helper methods for top videos and competitor research. However, the description overstates capabilities in two areas. First, it claims searching 'channels' directly, but the implementation only performs YouTube search and extracts channel names/links from returned video items; there is no dedicated channel-search functionality. Second, it claims support for 'rankings and trends,' but the implementation only exposes search, top-videos based on search ordering, and competitor aggregation—there is no explicit trend or rankings API. So this is a partial description-behavior mismatch due to overstated capabilities rather than a wholly different purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill declares access to an API key and implies networked execution, but it does not define an explicit tool scope such as allowed-tools or permissions. In an agent environment, this can cause overbroad execution authority or unclear policy enforcement, increasing the chance that the skill can access network or secret-bearing capabilities beyond what reviewers and users expect.

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/youtube_client.py (reported line 24)May include surrounding context.

python
class YouTubeClient:
    """AIsa YouTube - YouTube SERP Scout API Client."""
    
    BASE_URL = "https://api.aisa.one/apis/v1"
    
    def __init__(self, api_key: Optional[str] = None):
        """Initialize the client with an API key."""

Static analysis

No suspicious patterns detected.