openspec-apply-change
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local
openspecCLI commands to list changes, retrieve status, and obtain implementation instructions. These are legitimate operations for the tool's stated purpose. - [PROMPT_INJECTION]: The skill processes project files which could contain indirect prompt injections that influence the agent's code changes. Ingestion points: Task lists and context files (specs, designs) read during the implementation loop. Boundary markers: None; the agent processes the file content directly without delimiters or safety instructions. Capability inventory: The skill can modify any file in the repository and execute predefined CLI tools. Sanitization: The skill does not validate or sanitize the content of the files before following the instructions contained within them.
Audit Metadata