kata-pause-work
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell utilities including
grep,find, andprintfto programmatically determine the current project phase and task status from local planning files. - [COMMAND_EXECUTION]: Executes a local Node.js script
scripts/kata-lib.cjsto retrieve configuration values, specifically checking if the environment permits committing planning documents to Git. - [COMMAND_EXECUTION]: Performs standard Git operations (
git add,git commit) to persist the handoff file, ensuring state is preserved across sessions. - [PROMPT_INJECTION]: Analysis identifies an indirect prompt injection surface (Category 8) where external data is incorporated into a handoff file for future consumption. 1. Ingestion points: Data is read from
.planning/STATE.mdand user-provided 'mental context' strings. 2. Boundary markers: The generated.continue-here.mdfile does not use specific delimiters to isolate external content. 3. Capability inventory: The skill can execute shell commands and local Node.js scripts. 4. Sanitization: Ingested data is written directly to the markdown template without explicit sanitization.
Audit Metadata