The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the openspec CLI tool to perform various project management tasks, including listing changes (openspec list), checking workflow status (openspec status), and retrieving generation instructions (openspec instructions).- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from the local environment to drive its logic. Evidence: 1. Ingestion points: Data is ingested from the JSON output of the openspec instructions command and from the content of completed dependency files. 2. Boundary markers: No explicit delimiters or safety instructions are used to separate ingested content from the agent's internal logic. 3. Capability inventory: The skill has the ability to execute CLI commands and write files to the local file system (outputPath). 4. Sanitization: The skill parses JSON data but does not perform sanitization or validation of the text content within those files before using it to generate new artifacts.

openspec-continue-change