The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the openspec CLI to perform operations such as creating new changes, checking status, and fetching artifact instructions. These operations involve executing shell commands with arguments derived from user input (the change name) and previous command outputs.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, which presents an attack surface for indirect prompt injection. Ingestion points: The agent reads JSON output from openspec status and openspec instructions, and parses the contents of project files identified as dependencies in SKILL.md. Boundary markers: The instructions include a specific directive to treat context and rules fields as constraints for the agent's own behavior rather than content to be copied into the resulting files, which serves as a basic boundary. Capability inventory: The skill has the ability to execute shell commands via the openspec CLI and write files to the local file system at paths determined by the CLI output. Sanitization: No explicit sanitization or escaping mechanisms are defined for the content extracted from dependency files or CLI instructions before they are processed by the agent.

openspec-ff-change