The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill reads external content including "work units", "source IDs", "acceptance criteria", and "authoritative project artifacts" as specified in SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions provided to the agent to disregard instructions embedded within the ingested data.
Capability inventory: The skill possesses the capability to execute tool-based commands such as "acceptance gates" and project-impact, and it can write data to HANDOFF.md.
Sanitization: The instructions do not mention any sanitization, filtering, or validation steps for the content found within the external work units.

production-executor