ensemble-patrol
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a wide range of local development tools and system commands including
npm run test,cargo test,npx eslint,npx tsc,cargo clippy, andcargo fmtto evaluate the codebase. - [DATA_EXFILTRATION]: The skill is designed to transmit project health data, including file paths, code snippets, and issue descriptions, to the Linear platform using MCP tools (
mcp__linear-server__save_issue). This behavior is consistent with the skill's stated purpose of integrating with project management workflows. - [EXTERNAL_DOWNLOADS]: The skill utilizes
git fetchto synchronize the local environment with a remote repository, which is a routine operation for a development agent. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it analyzes arbitrary codebase content and git diffs.
- Ingestion points: Files in
src/andsrc-tauri/and output fromgit diff. - Boundary markers: None used to separate project data from instructions.
- Capability inventory: Includes the ability to create/modify projects and issues on Linear via MCP.
- Sanitization: No explicit sanitization or filtering of codebase content is mentioned before processing.
Audit Metadata