The Agent Skills Directory

[SAFE]: No security issues detected. The skill's functionality is focused on documentation management and knowledge retrieval using vendor-specific tools and repositories.
[COMMAND_EXECUTION]: The skill uses the qmd command-line tool to perform searches and queries within the local knowledge workspace. These commands are part of the intended primary purpose of the skill.
[PROMPT_INJECTION]: The skill describes a workflow that ingests external data sources like emails and web content into a searchable knowledge base. This creates a surface for indirect prompt injection from those sources, which is a common characteristic of knowledge management systems and is handled by the agent's internal safety guardrails.
Ingestion points: External content (emails, web, transcripts) stored in ~/dev/secondbrain/raw/ and project mirrors.
Boundary markers: None explicitly mentioned for the search tool outputs.
Capability inventory: Uses the qmd CLI for hybrid search and querying.
Sanitization: Not specified for external content ingested into the brain.

knowledge-workspace