migrate-cookiecutter
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content by reading the existing repository's source code and configuration files to determine the migration plan.
- Ingestion points: The skill reads the repository layout, source code files, data directories, and existing configuration files (e.g.,
pyproject.toml,setup.py,Makefile) as described inSKILL.md. - Boundary markers: Absent. The instructions do not include delimiters or specific warnings to ignore embedded instructions within the ingested repository data.
- Capability inventory: The skill possesses the capability to move or rename files (
git mv), create new files (pyproject.toml,app/main.py), and execute shell commands (uv sync,uv run pytest,ruff). - Sanitization: Absent. The skill interpolates information from the original repository into new package structures without explicit sanitization or validation of the content.
- [DYNAMIC_EXECUTION]: The skill generates and subsequently executes script content during the migration process.
- Evidence: The workflow involves creating
app/main.py(a Streamlit application) andpyproject.tomlbased on templates. The agent is then prompted to run these scripts usinguvandstreamlitto verify the migration. - [EXTERNAL_DOWNLOADS]: The skill fetches migration and structure standards from the author's official repository at
https://github.com/cedanl/.github/tree/main/standards. - [COMMAND_EXECUTION]: The skill uses various shell commands to perform the migration and verification steps, including
git mvfor file renames,uv syncfor dependency management, andpytestandrufffor code quality checks.
Audit Metadata