board-minutes
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its document processing and summarization workflow.
- Ingestion points: Meeting agendas, slide decks, and pre-read materials provided by the user (Step 3) are ingested and summarized to populate the minutes draft.
- Boundary markers: The instructions do not define specific delimiters, XML tags, or "ignore embedded instructions" warnings for the content extracted from external materials.
- Capability inventory: The skill performs file writes to local matter-specific folders (~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/) and accesses meeting metadata via calendar connectors.
- Sanitization: There is no explicit requirement to sanitize or validate the content of user-uploaded files before they are processed by the agent, allowing malicious instructions embedded in documents to potentially influence agent behavior.
Audit Metadata