deal-team-summary
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting findings from previous pipeline steps to generate summaries. 1. Ingestion points: Loads findings from diligence-issue-extraction and context from deal-context.md. 2. Boundary markers: Uses structured Markdown templates with role-specific headers (e.g., Executive, Deal Lead) and blockquotes. 3. Capability inventory: The skill writes summary files to matter-specific project directories within the ~/.claude/ configuration path. 4. Sanitization: No explicit content sanitization or validation is mentioned in the instructions.
Audit Metadata