kata-add-phase

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes external issue files (via the --issue flag) and interpolates the 'title' field directly into the ROADMAP.md and STATE.md files. This creates a surface where malicious instructions in an issue file could be introduced into the project's planning context.\n
  • Ingestion points: External Markdown files located in .planning/issues/open/.\n
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are used when interpolating the issue title into the roadmap.\n
  • Capability inventory: The skill can create directories, write to local project files, and execute local maintenance scripts.\n
  • Sanitization: While the skill sanitizes descriptions for directory slugs (kebab-case), the full description is written to project files without sanitization.\n- [Command Execution] (SAFE): The skill utilizes standard shell utilities (grep, sed, mkdir) and executes a local helper script (node scripts/kata-lib.cjs). These operations are consistent with the skill's purpose and are limited to the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 08:19 PM