boardroom
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files (strategy briefs) to drive its complex multi-role deliberation logic. * Ingestion points: Reads brief content from
~/.claude/briefs/<file>and organizational data fromcompany-context.md. * Boundary markers: The instructions do not define any delimiters or safety markers to isolate instructions within the brief from the skill's control logic. * Capability inventory: The skill writes output to the filesystem (~/.claude/boardroom/) and invokes other commands or agents (/em:challenge,/cs:decide, etc.) based on the processed content. * Sanitization: No evidence of sanitization or validation of the input brief's content before processing.
Audit Metadata