Back to skill

Security audit

Mc Db Discovery

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Mission Control database debugging checklist, with local SQLite inspection that fits its stated purpose.

Install only if you want an agent to inspect your local Mission Control database path and recent tasks while debugging schema issues; review any proposed backend schema changes before applying them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

File System Enumeration

Medium
Category
Data Exfiltration
Content
---

- Step 1: When DB file not found at expected path, trace createDb() calls in server code to find the resolvedPath (defaults to ~/.mc/data/mission-control.db).
- Step 2: Verify DB existence with: ls -la ~/.mc/data/mission-control.db
- Step 3: Inspect schema with: sqlite3 ~/.mc/data/mission-control.db ".schema tasks"
- Step 4: Check actual column names (e.g., 'state' vs 'status'); adjust frontend types or backend schema accordingly.
- Step 5: Validate data inserted correctly: sqlite3 ~/.mc/data/mission-control.db "SELECT * FROM tasks ORDER BY timestamp DESC LIMIT 5;"
Confidence
60% confidence
Finding
Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.

Static analysis

No suspicious patterns detected.