optimistic-update-rollback-contracts
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides ripgrep (
rg) commands to search for specific code signatures related to optimistic updates (e.g.,onMutate,getQueryData,tempId) within the project's source directories. These commands are for local code discovery and analysis. - [EXTERNAL_DOWNLOADS]: The skill references documentation and guides from trusted organizations and well-known services including React, Vercel, TanStack, and Apollo GraphQL. These links provide implementation context for the agent and are documented neutrally.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve searching and reading code from the user's project, which constitutes untrusted input.
- Ingestion points: Files located in the
src/andapp/directories. - Boundary markers: None are specified to separate user code from agent instructions.
- Capability inventory: The skill focuses on using
rgfor search; it does not request capabilities for network egress or file modifications across the scripts. - Sanitization: No validation or sanitization of the searched code is performed.
Audit Metadata