T08 · Insecure Dependencies
Warning
- Location
SKILL.md:122- Finding
Unpinned External Executable Registered as a Trusted MCP Server
- Content
View full analysis
- Remediation
View remediation
Security audit
Goodrp
Security checks for vulnerabilities and agentic risk
Overview
The skill matches its stated purpose, but it asks users to install and trust an unverified local GoodRP executable that can read current media activity and publish it to Discord.
Install only if you trust the GoodRP upstream executable and can verify the release yourself. Be cautious with auto-show because it can share future media activity on Discord automatically, and avoid enabling the HTTP API unless you need it and it remains bound to localhost.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Rogue AgentSelf-Modification, Session Persistence
- 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
Findings (4)
Agent Config Directory Access
High
- Category
- Agent Snooping
- Confidence
- 90% confidence
- Finding
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
- Content
Antigravity
Add to
~/.gemini/config/mcp_config.json:json { "mcpServers": {
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The description explains that the skill can display current media on Discord but does not prominently warn that song/video titles and app names may be broadcast to others. Because this skill handles potentially sensitive media consumption data, users may unknowingly expose personal interests, habits, or private content if the privacy implications are not made explicit before use.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The catch-all trigger 'Anything related to detecting the user's current media or Discord Rich Presence' is overly broad and can cause the skill to activate for loosely related requests. In this skill's context, unintended invocation is meaningful because the exposed tools can query current media and alter Discord presence, which may disclose or broadcast private listening/viewing activity without clear user intent.
- Content
Session Persistence
Medium
- Category
- Rogue Agent
- Confidence
- 60% confidence
- Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
- Content
md ## Setup Requirements 1. **GoodRP installed** — Download from https://github.com/isam-ahmed0/GoodRP/releases 2. **Discord Application ID** — Create at https://discord.com/developers/applications 3. **GoodRP running** — Either: - GUI mode with auto-show enabled, OR - Headless mode with `--mcp` flag (or `--mcp --api` for HTTP access)
Static analysis
No suspicious patterns detected.