Security audit

Tasks.md Sprint Sync

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently syncs project planning checklist text and does not show hidden, networked, persistent, or credential-related behavior.

Installers should understand that apply mode rewrites the selected project's Current phase and In progress list in the chosen TASKS.md file. Use report mode first and point PLAN_FILE and TASKS_FILE only at the intended project files, preferably under version control.

A.I.G

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

SkillSpector

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 (1)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill performs file reads and writes but does not declare any explicit tool scope or permission boundary. That means an agent may execute it with broader filesystem access than intended, increasing the chance of modifying arbitrary files if inputs such as PLAN_FILE or TASKS_FILE are pointed at unexpected paths.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.