core-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides standard shell commands for managing a development lifecycle, including Git synchronization (fetch, merge, add, commit, push) and NPM script execution (test, build, dev, type-check).
  • [COMMAND_EXECUTION]: Includes a process management utility command (lsof -ti:PORT | xargs kill) used to clean up local development servers after verification steps.
  • [SAFE]: Implements a defensive check that verifies the Git remote URL contains the author's username (travisjneuman) before permitting automated code pushes, serving as a safeguard against accidental updates to external repositories.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and act upon data from project planning files. Ingestion points: File paths such as .planning/PROJECT.md, tasks/*.md, ROADMAP.md, and phase-specific plans. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for these files. Capability inventory: Automated Git commits/pushes, NPM script execution, and process termination. Sanitization: No specific validation or escaping mechanisms are mentioned for the content of the processed planning files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:28 PM