gsd-reapply-patches
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses bash script snippets to locate backup directories within various standard configuration paths (e.g., $HOME/.config/opencode/gsd-local-patches). These shell operations are limited to directory existence checks.
- [PROMPT_INJECTION]:
- Ingestion points: Reads configuration metadata from
backup-meta.jsonand content from user-modified patch files stored in local configuration directories. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the ingested file content.
- Capability inventory: The skill has permissions for file system read/write operations, directory detection via shell, and the ability to spawn sub-agents for task execution.
- Sanitization: No explicit sanitization, validation, or filtering is performed on the content being merged from the patch files.
Audit Metadata