The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple commands using the openspec CLI tool, including openspec new, openspec status, and openspec instructions. These operations are essential to the skill's primary purpose of managing project artifacts and tracking implementation progress.- [PROMPT_INJECTION]: The skill exhibits a potential vulnerability to indirect prompt injection (Category 8). Ingestion points: It reads project background, artifact-specific rules, and instructions from the JSON output of the openspec instructions command, as well as the contents of completed dependency files (Step 4a). Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded commands within the ingested data. Capability inventory: The skill possesses the ability to execute shell commands via the openspec CLI and write new files to the system based on provided templates. Sanitization: There is no mention of sanitizing or validating the external content before it is used to guide the agent's file generation process.

openspec-ff-change