The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a framework for aggregating and processing data from various Obsidian notes and configuration files, creating a vulnerability surface for indirect prompt injection.
Ingestion points: The agent is instructed to read note content and metadata, including properties and frontmatter, to build dynamic views and summaries.
Boundary markers: The instructions do not specify the use of delimiters or warnings to separate external note data from the agent's internal reasoning or instructions.
Capability inventory: The skill allows the agent to read file paths, metadata, and contents across the vault and write synthesized results to .base files.
Sanitization: There is no evidence of validation or sanitization requirements for properties or content derived from potentially untrusted note sources before they are processed by the agent.

obsidian-bases