easy-cheese-setup
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a Python Zip Application (
easy-cheese-setup.pyz) and various Hallouminate CLI commands (hallouminate init-repo,hallouminate daemon restart,hallouminate index). These operations are fundamental to the skill's purpose and are protected by a required confirmation flow. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by scanning the local filesystem for specific directories and reading local configuration files, creating a surface for indirect instructions.
- Ingestion points: Reads the Hallouminate configuration file (defaulting to
~/.config/hallouminate/config.toml) and performs a filesystem scan to identify.cheesedirectories for registration. - Boundary markers: The skill implements a dry-run pattern via the
doctorcommand and instructions that explicitly require the agent to "Report proposed changes" and "Ask the user for confirmation" before using the--applyflag. - Capability inventory: The skill has the capability to execute local scripts and CLI tools that modify configuration files and restart background daemons.
- Sanitization: The instructions do not specify sanitization or validation logic for the paths or configuration values discovered during the scan.
Audit Metadata