openspec-new-change
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local environment by executing commands through the
openspecCLI tool, such as creating new change scaffolds and retrieving status updates. - [INDIRECT_PROMPT_INJECTION]: The skill uses input from the user to determine parameters for CLI commands, creating a potential surface for indirect injection.
- Ingestion points: User descriptions of features or fixes are processed to derive identifiers for the
openspeccommands inSKILL.md. - Boundary markers: No explicit delimiters are used to wrap the user-derived content within the command strings.
- Capability inventory: The skill possesses the capability to execute shell commands via the
openspecbinary. - Sanitization: The skill contains a mandatory guardrail requiring the agent to validate that the generated name is in 'kebab-case' before proceeding, which prevents the use of shell metacharacters or redirection operators.
Audit Metadata