xy-toolchain

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides detailed instructions for using the xy CLI and associated package-* hooks to manage TypeScript development workflows. These operations involve expected file system interactions such as compiling source code, running linters, executing tests with Vitest, and cleaning build directories.
  • [INDIRECT_PROMPT_INJECTION]: The xy work command set facilitates the synchronization of local work items with GitHub Issues. This creates a surface where external data (issue titles and descriptions) is brought into the tool's context.
  • Ingestion points: Local JSON storage in .xy/work/items/ and remote data from GitHub Issues accessed via the gh CLI.
  • Boundary markers: The documentation does not specify the use of delimiters or specific instructions for the agent to ignore embedded commands within the synced content.
  • Capability inventory: The toolchain has the ability to write to the file system, execute build/test commands, and interact with the GitHub API.
  • Sanitization: There is no mention of specific sanitization or validation protocols for the external data ingested during the sync process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 10:32 PM
Security Audit — agent-trust-hub — xy-toolchain