paper-bootstrap

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a command-line interface via a Python script (scripts/init_paper_layout.py) to automate directory setup. The script uses standard pathlib features and includes safety checks to avoid following symlinks or overwriting existing files.
  • [DATA_EXPOSURE]: The skill operates entirely on the local file system at a path specified by the user. It does not perform any network operations or access sensitive system paths (like .ssh or .aws).
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the current directory before creating layout files. While this involves reading local file metadata, the risk is negligible as the tool does not execute content found within those files and the layout script uses exclusive creation flags to prevent clobbering existing data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 05:25 AM