Security audit

Ouroboros

Security checks for vulnerabilities and agentic risk

Overview

The skill is an explicit relay to an external Ouroboros service, but it installs and runs an unpinned third-party MCP package and forwards user/channel context with limited control.

Review this before installing. Only use it if you trust the Ouroboros MCP service and package publisher, understand that messages plus channel/guild/user identifiers may be sent to that service, and can run the MCP server in a constrained environment. Prefer a pinned, reviewed package version and avoid giving it access to unrelated repositories, credentials, or home-directory data.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:13
Finding: Untrusted External MCP Service Takes Control of Agent Request Handling
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Error

Location: SKILL.md:30
Finding: Unpinned Third-Party Package Is Downloaded and Executed Through uvx
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly instructs forwarding channel_id, guild_id, user_id, and optionally message_id to an external MCP tool, but it provides no user-facing disclosure, consent, or data-minimization guidance. This creates a real privacy and data-handling risk because users may trigger the skill with a simple prefix without understanding that identifiers and message content are being transmitted to a separate service.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: The description hard-codes activation only when a message starts with ooo, but it does not impose a human language or locale restriction. Because this is a symbolic command prefix rather than a language/locale policy, this likely does not violate organizational language policy.
Content: No source excerpt is available for this finding.