setup-slipbox
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs necessary dependencies using standard package managers. It executes
pip install youtube-transcript-apiandnpm install -gfor thedefuddleandfirecrawl-clipackages. The instructions explicitly state that the agent must ask for user permission before proceeding with each installation, and it provides a detection-only check script (scripts/check-prereqs.sh) to verify presence before attempting any download. - [COMMAND_EXECUTION]: The skill uses shell commands and scripts to manage the local environment. It runs prerequisite checks, performs installations, and manages a local CLI tool (
.slipbox/bin/slipbox). This CLI tool wraps Git operations (e.g.,git add,git commit) to provide version control for the vault's data, utilizing an isolated index to ensure only intended paths are affected. - [DYNAMIC_EXECUTION]: The
slipboxCLI script uses an internal mechanism to pipe hardcoded Python code blocks to thepython3interpreter for complex logic such as JSON parsing, frontmatter manipulation, and path sanitization. This allows the tool to perform advanced data operations without relying on external compiled binaries. - [SAFE]: The skill demonstrates a high level of security awareness through its implementation. It includes robust path sanitization (
_safe_vault_path) to prevent directory traversal attacks, uses atomic write operations via temporary files to prevent data corruption, and explicitly disables model invocation in the frontmatter to ensure deterministic and safe setup behavior. Additionally, it avoids handling credentials directly, instead pointing users to official configuration tools for services like Firecrawl.
Audit Metadata