The Agent Skills Directory

[SAFE]: The skill implements a set of specialized tools (mcp__flow-nexus__*) for user-centric operations such as profile updates and file storage. These tools are aligned with the skill's stated purpose and operate within the expected platform context.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its handling of external data. Ingestion points: Data enters the agent context through user profile retrieval and file storage access via mcp__flow-nexus__user_profile and storage tools. Boundary markers: There are no explicit instructions or delimiters to distinguish between system instructions and processed data content. Capability inventory: The agent can perform file writes via mcp__flow-nexus__storage_upload and initiate sub-agent consultations through mcp__flow-nexus__seraphina_chat. Sanitization: The skill does not define methods for validating or sanitizing ingested content before it is used in subsequent operations.

agent-user-tools