The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process external task data (beads), which establishes a potential surface for indirect prompt injection. \n- Ingestion points: The agent reads external content via the gc bd show and gc hook commands (SKILL.md).\n- Boundary markers: Absent; there are no instructions to use specific delimiters or ignore embedded instructions within the bead content.\n- Capability inventory: The skill utilizes the gc bd update and gc bd close commands to modify the status and metadata of work items (SKILL.md).\n- Sanitization: Absent; the skill does not describe any validation or sanitization steps for the data processed from the CLI output.

gc-work