Back to skill

Security audit

standup-mobi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local absence-coverage planner whose file reads and writes are disclosed and aligned with its purpose.

Before installing, expect this skill to create and edit local coverage-planning files. Do not put passwords, keys, tokens, or sensitive credential values into duties.json, notes, runbooks, or generated checklists; use vault entry names or system names only. Store generated runbooks and checklists in an appropriate private workspace if they describe internal operations.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill documents CLI commands that read and write local files (team.json, duties.json, output checklists) but does not declare any permissions or allowed-tools scope. That creates a mismatch between stated and actual capabilities, which can lead to overbroad agent execution or unsafe deployment assumptions because users and orchestrators cannot constrain filesystem access explicitly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The checklist command writes accumulated duty content, including free-form notes from duties.json, to a user-specified output file. Although the tool prints that it wrote the file, there is no prior warning that the generated file may contain sensitive operational details or should be handled carefully.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.