The Agent Skills Directory

[SAFE] (SAFE): The skill contains no malicious instructions, obfuscation techniques, or exfiltration logic. Its operations are consistent with its stated purpose of document management.\n- [NO_CODE] (SAFE): No executable code, scripts (Python, Node.js, Shell), or binary files are included within the skill package.\n- [COMMAND_EXECUTION] (SAFE): The skill utilizes domain-specific slash commands like /speckit.clarify, which are treated as functional tool invocations within the specification kit rather than arbitrary command-line execution.\n- [PROMPT_INJECTION] (SAFE): There is a minimal surface for indirect prompt injection via the project files the skill is designed to read. 1. Ingestion points: Reads files in the specs/ directory. 2. Boundary markers: None explicitly defined in the instructions. 3. Capability inventory: Limited to local file system writes in the project directory. 4. Sanitization: Relies on standard agent processing of markdown content.

complete-spec