evo-brainstorming
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown without any embedded scripts or executable code.
- [DATA_EXFILTRATION]: The skill reads local project files, such as 'docs/constitution.md' and 'docs/ledger.jsonl', to establish context. It writes its output to a local design document. No network activity, external data transmission, or unauthorized credential access was detected.
- [PROMPT_INJECTION]: Directive language such as 'HARD-GATE' and 'MUST' is used to enforce the internal brainstorming logic and prevent premature implementation. These instructions do not attempt to override the agent's core safety guidelines or extract system prompts.
Audit Metadata