The Agent Skills Directory

[SAFE]: The skill is composed strictly of markdown documentation. It contains no executable scripts (Python, JavaScript, shell) or configuration files that perform actions on the host system.
[EXTERNAL_DOWNLOADS]: The instructions reference external documentation resources hosted on docs.stackbone.ai. These are official vendor resources belonging to the author 'stackbone' and are used for retrieving operational metadata and documentation via MCP tools.
[COMMAND_EXECUTION]: The skill mentions CLI commands like claude mcp add and stackbone hitl as part of standard setup and usage instructions for the Stackbone platform. No unauthorized or hidden command execution patterns were found.
[PROMPT_INJECTION]: While the skill includes triggers related to 'blocking prompt injection,' it does not contain instructions to bypass safety filters or override agent behavior maliciously. It is a utility for enhancing security.

stackbone-guardrails