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 executes local commands using the
openspecCLI to manage change requests and artifacts. These operations are project-specific and do not involve administrative privileges or access to sensitive system directories.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to define change parameters, creating a potential surface for indirect injection.\n - Ingestion points: User descriptions of features or fixes (SKILL.md, Step 1).\n
- Boundary markers: No explicit delimiters are used in the prompt interpolation.\n
- Capability inventory: Executes local shell commands via the
openspecCLI (SKILL.md, Steps 2-5).\n - Sanitization: The skill instructs the agent to transform user input into a kebab-case string, effectively sanitizing the input for use as a command-line argument.
Audit Metadata