skills/juxt/claude-plugins/goal-tree/Gen Agent Trust Hub

goal-tree

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of instructional markdown content. It defines a conceptual framework ('Goal Trees') for structuring logical tasks and testing for sufficiency.
  • [PROMPT_INJECTION]: The skill uses RFC 2119 terminology (MUST, SHOULD) to define how the agent should structure its internal reasoning. These instructions are within the expected scope of a planning skill and do not attempt to bypass safety filters or override system-level instructions.
  • [DATA_EXPOSURE]: No sensitive file paths, environment variables, or hardcoded credentials were detected.
  • [EXTERNAL_DOWNLOADS]: The skill does not reference external URLs, download remote scripts, or specify package dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 07:24 PM