ideation
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests unstructured user-provided 'brain dumps' to inform its analysis and documentation. This risk is effectively managed by a confidence-gated pipeline and the mandatory use of the 'AskUserQuestion' tool for all decision points and approvals. Ingestion points occur during Phase 1 (Intake) and Phase 3 (Analysis). Security relies on human-in-the-loop verification of all generated artifacts before subsequent execution is suggested.
- [NO_CODE]: The skill consists entirely of markdown instructions and reference templates. It does not include any Python scripts, Node.js packages, or shell scripts. This significantly limits the attack surface by preventing direct execution of malicious logic, unauthorized network operations, or persistence mechanisms within the skill itself.
Audit Metadata