openspec-ff-change
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
openspecCLI commands to scaffold projects and manage artifact states. These commands are essential to the skill's primary purpose and target the vendor's own command-line utility. - [PROMPT_INJECTION]: The skill processes user-provided descriptions to guide the generation of artifact content, which represents an indirect prompt injection surface.
- Ingestion points: User input is gathered via the AskUserQuestion tool in the initial step.
- Boundary markers: The skill does not explicitly use delimiters or "ignore instructions" warnings for the user-provided descriptive content.
- Capability inventory: The skill has the ability to create and modify files on the local system through the OpenSpec CLI.
- Sanitization: The instructions mitigate direct command injection by requiring the agent to transform user input into a kebab-case format for CLI naming arguments.
Audit Metadata