Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Security audit
LYGO TV
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed LYGO TV pointer and website embed package; its local scripts are read-only printers, while the browser embed clearly discloses its network activity.
Before installing, understand that the local skill is mostly a pointer and snippet printer, but any site using the embed will load active third-party browser content and a mutable channel catalog. Review embed/README.md and use the vendored/pinned option if your site needs tighter control; donation links are optional and not required for the player.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'shell' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill exposes PayPal, Patreon, and referral/join URLs that are not necessary to fulfill its stated purpose of providing a TV player and embed code. While not a code-execution flaw, this creates an unnecessary monetization and trust-manipulation surface that can mislead users or divert them to external sites unrelated to the core function.
- Content
Context-Inappropriate Capability
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
Implementing a dedicated 'donate' command expands the skill beyond its declared scope and provides a built-in path to solicit money or external engagement. In an agent ecosystem, this kind of scope creep is risky because users may trust the skill as a utility and not expect transactional or promotional behavior.
- Content
Static analysis
No suspicious patterns detected.