literate-programming

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for initializing projects using external Git submodules from the author's own GitHub organization (dbosk/makefiles and dbosk/didactic). These are official vendor resources necessary for the build system.
  • [COMMAND_EXECUTION]: The skill contains extensive documentation for using standard development tools, including 'make', 'notangle', 'noweave', 'poetry', and 'latexmk'. These tools are used for tangling source code and weaving documentation as part of the intended literate programming workflow.
  • [DYNAMIC_EXECUTION]: The skill involves the generation of executable source code (e.g., .py files) from literate source files (.nw) via 'notangle'. This is the primary function of the skill, and the instructions emphasize human review of the narrative structure and logic during this process.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on external '.nw' files which serve as an ingestion surface.
  • Ingestion points: Instructions in 'SKILL.md' and 'references/multi-directory-projects.md' target '.nw' files.
  • Boundary markers: The skill enforces strict noweb syntax (documentation chunks starting with '@' and code chunks with '<>=') which serves as structural delimitation.
  • Capability inventory: The skill uses tools to write files (tangle) and execute tests (pytest/make).
  • Sanitization: Guidelines require maintaining narrative quality and pedagogical order, which encourages human oversight of the generated content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 11:34 PM