The Agent Skills Directory

[SAFE]: The skill defines a documentation management workflow using standard markdown templates. No indicators of malicious activity such as credential theft, remote code execution, or unauthorized network operations were detected.\n- [PROMPT_INJECTION]: The skill instructions define operations that ingest external data sources, including tickets, specifications, and design briefs. While this creates a surface for indirect prompt injection, it is essential for the primary purpose of the skill and is handled via a structured review process.\n
Ingestion points: Operations inspect and converge read external files such as originating tickets, acceptance lists, and existing product documentation.\n
Boundary markers: The instructions do not specify explicit delimiters or 'ignore' commands for the ingested external content.\n
Capability inventory: The skill uses tools for repository exploration, documentation implementation, and verification of observable behavior.\n
Sanitization: No specific content filtering or sanitization of ingested data is described, as the agent is expected to interpret and summarize the information.

living-spec