The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the bd CLI tool to create project epics. This command execution is consistent with the skill's purpose of integrating with the Beads Issue Tracker and does not involve elevated privileges.
[PROMPT_INJECTION]: The skill ingests conversation context and codebase data to generate summaries. While this represents an indirect injection surface, the risk is minimized as the agent synthesizes the information into a structured template. Ingestion points: conversation history and repo files (SKILL.md). Boundary markers: absent. Capability inventory: shell execution of bd command. Sanitization: handled by the agent's synthesis logic.
[SAFE]: No evidence of obfuscation, hardcoded credentials, data exfiltration, or persistence mechanisms was found in the provided files. The skill metadata and implementation align with its stated function.

to-epic