brainstorming
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious obfuscation, remote code execution patterns, or hardcoded credentials were found. The skill primarily provides logical instructions for a design workflow.
- [NO_CODE]: The skill consists entirely of instructional Markdown and does not include any scripts, executables, or automated installation steps.
- [COMMAND_EXECUTION]: The skill performs local filesystem operations by saving design documents to
~/.agents/brainstorming/. This is a standard functional task for design documentation and is assessed as safe within the context of the skill's purpose. - [PROMPT_INJECTION]: Indirect Prompt Injection surface detected. Ingestion points: Step 1 (reading project files, docs, and commits). Boundary markers: Absent. Capability inventory: Step 5 (writing design documents to local disk). Sanitization: Absent. This surface is inherent to the skill's function and is managed by the agent's core safety protocols.
Audit Metadata