openspec-continue-change
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspecCLI tool locally to list changes, check status, and retrieve instructions. While these are intended vendor functionalities, the use of user-suppliedchange nameparameters in shell commands assumes the underlying environment handles shell escaping to prevent command injection. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: The agent reads content from local project files identified as
dependenciesin theopenspecCLI output. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested files.
- Capability inventory: The agent has the capability to write to the local file system and execute CLI commands.
- Sanitization: No validation or sanitization of content from dependency files is performed before it is processed by the model.
Audit Metadata