openspec-new-change
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing local shell commands through the openspec CLI to manage changes, check status, and retrieve instructions. These operations are the primary function of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions and change names which are then used as arguments in shell commands.
- Ingestion points: The
AskUserQuestiontool is used to collect the user's change description inSKILL.md. - Boundary markers: The skill instructs the agent to enforce a kebab-case naming convention for derived change names.
- Capability inventory: The skill can execute various shell commands via the
openspecCLI. - Sanitization: A guardrail is included to ensure the name is in kebab-case and to ask for a valid name if it is not, which serves as a filter against special characters used in shell injection attacks.
Audit Metadata