create-plan

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate development workflow tasks including reading project research documents, extracting Git metadata, and updating ticket statuses via CLI tools. These actions are standard for an implementation planning agent and occur within the project environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from research documents and ticket descriptions to inform the planning process. While it lacks explicit sanitization or boundary markers, this risk is inherent to its primary purpose of processing project context. The capabilities used (writing plans, posting comments) do not pose a high risk in this context, and the behavior is typical for LLM-based planning tools.
  • [EXTERNAL_DOWNLOADS]: Sub-agents within the skill, such as the external-research and codebase-pattern-finder agents, utilize tools like WebSearch and WebFetch to research libraries and frameworks. These operations are scoped to technical research and are expected behaviors for the research roles defined in the skill assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 09:29 PM
Security Audit — agent-trust-hub — create-plan