The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from various project files, which constitutes a potential ingestion surface for instructions embedded in source code or documentation.
Ingestion points: Reads files from tests/unit/*.test.ts, src/domain/timeline.ts, and docs/design/stage-specs/*.md to extract test names, event IDs, and requirements.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these file contents.
Capability inventory: The skill has the capability to read local files, write to a documentation file (docs/tests/coverage-matrix.md), and update an audit ledger through an 'audit-item' mechanism.
Sanitization: No specific sanitization or escaping of the extracted strings is mentioned before they are written to the output artifacts.
[COMMAND_EXECUTION]: The skill documentation mentions the command npx vitest run within a sample table structure for 'Table 3: DoD ↔ Gate'. This is listed as a reference value to be included in the generated markdown report and is not an instruction for the agent to execute the command directly during skill runtime.

coverage-matrix