think-brainwriting
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions, templates, and examples. It does not include any scripts, binaries, or shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided ideation prompts. As an ideation tool, it acts as a passive processor of input. However, since the skill has no capabilities for network access, file system modification, or command execution, the risk of an injection causing harm is negligible.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No network operations (curl, wget, fetch) or sensitive file path references (credentials, SSH keys, env files) were detected. The skill operates entirely within the text context of the agent.
- [REMOTE_CODE_EXECUTION]: There are no package installation commands (npm, pip) or remote script execution patterns. All referenced resources trace back to the vendor's own repository (product-on-purpose) or academic citations.
Audit Metadata