skills/atxp-dev/cli/atxp-git/Gen Agent Trust Hub

atxp-git

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill invokes npx atxp@latest to download and execute the ATXP command-line interface from the NPM registry. This is the primary mechanism for repository management.
  • [COMMAND_EXECUTION]: The skill uses shell commands via npx and git to perform operations such as creating, cloning, and pushing to repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes content from external Git repositories.
  • Ingestion points: Files and metadata within cloned Git repositories (SKILL.md).
  • Boundary markers: None specified for handling untrusted repository content.
  • Capability inventory: Includes filesystem write and network access via git, and command execution via npx (SKILL.md).
  • Sanitization: Relies on native Git functionality and server-side JWT authentication; no explicit content sanitization is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:35 AM