competency-unpacker

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a pure prompt-based assistant for curriculum planning. It takes text-based input (curriculum descriptors) and provides text-based output based on established educational frameworks.
  • [NO_CODE]: There are no executable scripts, shell commands, or external dependencies included in the skill. All logic is contained within the natural language prompt instructions.
  • [DATA_EXPOSURE]: The skill does not access sensitive local files, environment variables, or credentials. It uses standard input fields for educational data which are processed within the agent's context.
  • [REMOTE_CODE_EXECUTION]: There is no evidence of remote script fetching, package installation, or dynamic code evaluation (eval/exec).
  • [PROMPT_INJECTION]: The prompt instructions are focused on educational persona and methodology. There are no patterns suggesting attempts to bypass safety filters or override system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:53 PM