openspec-apply-change
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspecCLI to list, check status, and get apply instructions, interpolating change names into shell commands. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection due to its processing of external content. 1. Ingestion points: Project artifacts defined in
contextFilesand dynamic instructions from CLI output. 2. Boundary markers: No delimiters are utilized to isolate external data from agent instructions. 3. Capability inventory: Ability to read and write files and execute shell commands via the OpenSpec tool. 4. Sanitization: No content validation or sanitization is performed on ingested data.
Audit Metadata