business-brainstorm
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform file system operations, such as creating directories and moving files between the skill's reference folder and the user's local configuration directory (
~/.config/makerskills/business-brainstorm/archive/) for data migration and archiving purposes. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including user-provided business ideas and references to past chats or documents. This creates an attack surface where malicious instructions could be embedded in the data to influence the agent's scoring or behavior.
- Ingestion points: Business ideas (user input), referenced past chats/documents, and portfolio configuration files located at
${MAKERSKILLS_CONFIG:-$HOME/.config/makerskills}/business-brainstorm/portfolio.local.md. - Boundary markers: No specific sanitization or delimiters are defined to isolate untrusted user input from the framework's instructions beyond the markdown structure.
- Capability inventory: File read, write, and move operations within the user's home configuration directory; orchestration of external tools including
/deep-research,/domain, and/last30days. - Sanitization: The skill does not describe any explicit sanitization, validation, or escaping of the input data before it is interpolated into the brainstorming process.
Audit Metadata