e2e-macos
Warn
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONCREDENTIALS_UNSAFEPERSISTENCEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
subprocessmodule to execute system commands includinggitfor repository management,sshfor remote machine access,launchctlfor service management, and Node.js tools likepnpmfor building the project. - [DYNAMIC_EXECUTION]:
macos-run.pyreads the full source code ofmacos-target.pyand executes it on the target machine (locally or via SSH) using thepython3 -ccommand. Additionally, it decodes a Base64-encoded shell script (e2e-install.sh) at runtime and executes it usingbashto perform the main installation steps. - [CREDENTIALS_UNSAFE]: The skill can read an Anthropic API key from a local file (defaulting to
~/.nanoclaw-e2e/anthropic_key) and transmit it to a target machine. On the target system, the key is written to a temporary file (.git/nanoclaw-e2e/credential) with restricted permissions before being utilized by the installer and subsequently deleted. - [PERSISTENCE]:
macos-service.pyprogrammatically creates and loads a macOS LaunchAgent plist in the user's~/Library/LaunchAgentsdirectory. This is used to ensure the NanoClaw service remains active and starts automatically within the user's GUI session. - [EXTERNAL_DOWNLOADS]: The skill clones external Git repositories using
git cloneandgit fetch. It resolves repository URLs from the local environment or user-supplied arguments, typically targeting GitHub. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect injection as it ingests and processes untrusted data from external Git repositories (commits, source files) and project metadata (e.g.,
package.json). - Ingestion points: Reads
package.json, Git repository contents, and commit SHAs inmacos-run.pyandmacos-target.py. - Boundary markers: Uses
shlex.quoteandshlex.jointo escape arguments when constructing shell commands. - Capability inventory: Includes the ability to write files, execute subprocesses (git, ssh, launchctl, bash), and create persistent services.
- Sanitization: Employs JSON-based communication between the operator and target scripts and uses standard shell escaping libraries.
Audit Metadata