Back to skill

Security audit

Coret Mind Map

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Coret mind-map assistant with clear safeguards around API keys, live edits, deletion, and sharing.

Install this only if you intend to let an agent use your Coret MCP connection to read and change mind maps. Use a test API key while trying it, confirm the workspace before live edits, and review deletion or public-sharing requests carefully.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Scope Creep

Low
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
- Get explicit confirmation immediately before `delete_map` or `delete_node`, unless the user already explicitly requested that exact deletion. Explain that deleting a node also deletes its descendants.
- Treat `batch_nodes` as destructive when it contains update or delete operations; summarize the affected branches before calling it.
- Do not broaden scopes, switch from test to live, or create a public share link silently.
- If a tool returns an auth, scope, validation, rate-limit, or quota error, report it plainly and stop retrying unchanged input.
- If a multi-step write fails partway, read the current map before retrying so completed operations are not duplicated.