board-of-directors
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands (
mkdir -p) to create a directory structure for managing session metadata and discussion logs within a specific project path. - [PROMPT_INJECTION]: The skill is designed to evaluate arbitrary 'proposals' and 'context' data. This creates an indirect prompt injection surface where malicious instructions in a proposal could attempt to influence the board's deliberation, although the 'Chief Security Officer' persona is explicitly tasked with detecting such patterns.
Audit Metadata