Flatnotes + Tasks.md GitHub Audit

• Outcome: Review
• Latest audit: Sep 10, 2026 · 10:46 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed local audit tool that reads configured Tasks.md and Flatnotes data, optionally queries GitHub through the gh CLI, and writes audit reports.

Install this only if you are comfortable with the agent reading your configured Tasks.md and Flatnotes directories and using any authenticated gh CLI session to query GitHub. Review the generated tmp report before asking the agent to apply any fixes.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence

Finding

The skill invokes local code and explicitly relies on environment variables (TASKS_ROOT, FLATNOTES_ROOT) plus external tooling (gh), but it does not declare any tool scope or permissions boundaries. In an agent setting, that increases the chance the skill is executed with broader filesystem or environment access than intended, allowing reads/writes against sensitive paths or use of inherited credentials without clear user visibility.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The quick-start example says it is 'report-only' but includes --write, which performs filesystem writes immediately without an adjacent warning. That mismatch can cause users or agents to run a mutating command under the assumption it is non-destructive, leading to unintended modification of workspace files or generated artifacts in automated environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 72% confidence

Finding

The script reads task and notes data from local paths derived from environment variables and, when --write is set, creates directories and writes Markdown/JSON audit files. While these actions are central to the audit purpose, this file lacks a docstring, comment, or user-facing notice describing the local data access and file creation behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

This code invokes the gh CLI to query GitHub, which transmits repository identifiers and authentication context over the network. In this file there is no confirmation prompt or user-facing notice before these external calls occur.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: scripts/audit.mjs:53