deal-team-summary
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses local file paths such as
~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.mdand matter-specific directories to retrieve context. This file access is restricted to the skill's defined workspace and is necessary for its stated purpose of summarizing legal deal data. - [COMMAND_EXECUTION]: No shell commands, external scripts, or system-level calls are present in the skill instructions. It functions strictly through natural language instructions to the AI agent.
- [PROMPT_INJECTION]: The skill instructions do not contain attempts to bypass AI safety filters, extract system prompts, or override agent constraints. The instructions focus on output formatting and content prioritization based on audience levels.
- [EXTERNAL_DOWNLOADS]: The skill does not initiate any network requests, downloads, or remote resource fetches. All data is handled locally within the platform's file system.
Audit Metadata