The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local commands using the 'openspec' CLI (e.g., 'openspec new change', 'openspec status', 'openspec instructions'). These operations are restricted to the local project environment and are necessary for the skill's primary function of generating project documentation. No unauthorized command patterns were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-provided descriptions to create change names and reads content from previously generated artifact files to inform the creation of new ones. Although it lacks explicit delimiters or sanitization steps for the content of these files, the instructions provide specific constraints that require the agent to use this information as project context rather than directly executing instructions embedded within them. The risk is minimized by the skill's adherence to structured templates and local execution scope.

openspec-propose