openspec-new-change
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local system by executing various subcommands of the
openspecCLI, such asnew change,status, andinstructions, which are used to manage project artifacts and workflows. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions to define change names and select workflow schemas.
- Ingestion points: User input gathered via the
AskUserQuestiontool in Step 1 (SKILL.md). - Boundary markers: None explicitly defined for the interpolation of user data into commands.
- Capability inventory: Execution of shell commands through the
openspecCLI (SKILL.md). - Sanitization: The skill includes instructions to convert user input into a kebab-case format and validate the name before execution, which serves as a functional security boundary against shell injection.
Audit Metadata