fobi28/Secure-Agent-Launcher

Block AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.

What's novel

Block AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.

Code Analysis

12 files read · 4 rounds

A macOS CLI wrapper that statically analyzes command-line arguments for paths matching a user-defined deny list and refuses to execute the command if any match, with audit logging and a Tkinter GUI for managing the deny list.

Strengths

Clean, well-tested code with zero external dependencies, proper dependency injection for testability, file locking for concurrent audit log writes, and a polished bilingual GUI with sensible defaults for sensitive paths.

Weaknesses

The 'blocking' mechanism is purely static argv parsing — it cannot detect sensitive file access via scripts, environment variables, or internal tool logic, making it a thin convenience wrapper rather than a real security boundary. The README overstates the security guarantees ('keeps your personal secrets safe') while the actual mechanism is easily bypassed.

Score Breakdown

Innovation

4 (25%)

Craft

71 (35%)

Traction

11 (15%)

Scope

59 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+1

Craft

Ci+0

Tests+8

Polish+0

Releases+0

Has License+5

Code Quality+24

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+2

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+3

Early Traction+0

Devto Reactions+0

Community Contribs+2

Scope

Commits+5

Languages+5

Subsystems+10

Bloat Penalty+0

Completeness+7

Contributors+6

Authored Files+8

Readme Code Match+3

Architecture Depth+3

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

MIT