atxp-git
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and executes the latest version of the 'atxp' CLI tool from the NPM registry using 'npx'. This is the vendor's official package used to interface with their repository hosting service.
- [COMMAND_EXECUTION]: Shell commands are executed via 'npx' and 'git' to perform repository operations such as creation, listing, cloning, and pushing. These commands are standard for the skill's stated purpose.
- [DATA_EXFILTRATION]: Network communication is established with 'git.mcp.atxp.ai' and 'atxp.code.storage' to facilitate Git operations and API requests. These endpoints are owned by the vendor (atxp-dev).
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks common to all Git-integrated tools.
- Ingestion points: Data enters the agent's context when repositories are cloned to the local filesystem (SKILL.md).
- Boundary markers: Absent; no specific instructions are provided to the agent to ignore instructions embedded within the processed repository files.
- Capability inventory: The agent has access to 'npx' for executing vendor tools and 'git' for version control operations (SKILL.md).
- Sanitization: No explicit sanitization or validation of the content within the cloned repositories is performed before processing.
Audit Metadata