codexmcp-claude-codex-collaboration
Fail
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the installation script for the
uvtool fromastral.sh. As this is a well-known service for development tools, the download itself is considered standard for the skill's purpose. - [REMOTE_CODE_EXECUTION]: The installation guide includes commands that pipe remote scripts directly into the shell for execution (
curl ... | shandirm ... | iex). This pattern is common in developer workflows but bypasses content validation before execution. - [REMOTE_CODE_EXECUTION]: The skill installs the
codexmcpserver directly from a third-party GitHub repository (github.com/GuDaStudio/codexmcp.git) usinguvxduring the setup process. - [PRIVILEGE_ESCALATION]: The Windows installation instruction utilizes the
-ExecutionPolicy ByPassflag to execute the remote script, which temporarily overrides PowerShell's security restrictions for that specific command execution. - [COMMAND_EXECUTION]: The
codextool allows the agent to execute coding tasks that can involve file system operations. The skill includes built-in safety documentation for sandboxing, defaulting to aread-onlymode and providing warnings for high-privilege modes likedanger-full-accessoryolo. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect injection as it ingests user prompts and reads files from the working directory to perform coding tasks.
- Ingestion points: Data enters the context via the
PROMPTparameter and files residing in thecdworking directory path. - Boundary markers: The skill explicitly instructs the agent in its system prompt to treat Codex output as a "unified diff patch" and "logical reference" only, and to verify all changes before implementation.
- Capability inventory: The skill can perform file writes and execute code through the Codex tool depending on the
sandboxparameter configuration. - Sanitization: Security relies on the provided sandbox levels and the requirement for manual review of tool outputs as described in the documentation.
Recommendations
- HIGH: Downloads and executes remote code from: https://astral.sh/uv/install.sh - DO NOT USE without thorough review
Audit Metadata