ingest-cwe-taxonomies
Ingest the official MITRE CWE database and generate per-domain security audit taxonomies for PromptKit. Use this skill when the user wants to update CWE taxonomies, ingest a new CWE version, or regenerate domain mappings from the CWE corpus.
You must read and execute the prompt file at
.github/prompts/ingest-cwe-taxonomies.prompt.md. Treat it as the
complete, self-contained instruction set for the CWE ingestion pipeline.
Inputs
- CWE source: A local path to a CWE XML file, or
latestto download the current release fromhttps://cwe.mitre.org/data/xml/cwec_latest.xml.zip. - Any overrides to the domain registry or mapping rules the user specifies.
Output
- Per-domain taxonomy files at
taxonomies/cwe-<domain>.md(13 domains) - Normalized CWE data at
data/cwe/<version>/ - Updated
manifest.yamlwith new taxonomy entries - Reusable ingestion script at
scripts/ingest-cwe.py - Diff report if a previous CWE version exists
Workflow
- Read
.github/prompts/ingest-cwe-taxonomies.prompt.mdbefore doing anything else. - Ask the user for the CWE source (path or
latest). - Follow all six phases defined in the prompt file: Acquisition, Normalization, Domain Mapping, Taxonomy Generation, Integration, and Verification.
- Do NOT skip the sanity checks in Phase 6.
Loading supporting files
microsoft/promptkit · MIT · Revision 942c121fea37
Be the first to comment
Share what worked or leave a question for the creator.