openspec-new-change
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local environment using the openspec CLI to manage project changes. It executes standard commands such as openspec new change, openspec status, and openspec instructions. These operations are restricted to the local filesystem and are consistent with the skill's primary purpose.
- [PROMPT_INJECTION]: The skill processes user-provided descriptions to generate identifiers for project changes. 1. Ingestion points: User description enters via the AskUserQuestion tool in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Command execution via openspec CLI throughout SKILL.md. 4. Sanitization: The skill implements a robust guardrail that requires user input to be converted into a validated kebab-case format, effectively preventing command injection and ensuring untrusted data cannot manipulate the underlying shell commands.
Audit Metadata