boardroom
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes deliberation briefs provided at
~/.claude/briefs/as part of its core workflow. This introduces a potential surface for indirect prompt injection if a brief contains malicious instructions intended to bias the simulated advisors or the synthesis process.\n - Ingestion points: Brief files located in
~/.claude/briefs/as described in SKILL.md.\n - Boundary markers: None specified; the skill instructions do not explicitly tell the agent to ignore instructions embedded within the brief data.\n
- Capability inventory: The skill performs local file reads from the briefs directory and company context, and writes output memos to
~/.claude/boardroom/.\n - Sanitization: No validation or escaping of the input brief content is performed before processing.
Audit Metadata