Back to skill

Security audit

PlanWright Control Plane

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent PlanWright workflow helper that uses an MCP control plane and audit ledger as part of its stated purpose, with no embedded code or hidden execution behavior found.

Install this only if you intend to use PlanWright as a shared control plane and are comfortable providing PLANWRIGHT_TOKEN. Treat recorded diffs, notes, test results, repository metadata, and context files as potentially persistent service data; avoid sending secrets, regulated data, or proprietary details unless your PlanWright retention and access controls are acceptable.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states that every action is written to a signed, hash-chained audit ledger, but it does not warn users that prompts, diffs, notes, test results, or repository metadata may be persisted and potentially contain sensitive information. In a multi-agent coding workflow, this increases the risk of unintentionally storing secrets, proprietary code details, or personal data in an audit system without informed user consent or handling guidance.

Content

No source excerpt is available for this finding.