The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the vstash Python package via pip install vstash. This is a core dependency and a resource associated with the tool's primary functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local files, directories, and external URLs which are ingested into memory for semantic search and Q&A.
Ingestion points: The vstash_add tool in SKILL.md and references/mcp-reference.md accepts paths and URLs for document ingestion.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified in the provided documentation.
Capability inventory: The skill includes capabilities for reading local files and fetching data from remote URLs (vstash_add), and exporting processed data (vstash_export) as seen in references/mcp-reference.md.
Sanitization: No specific sanitization or filtering of the ingested content is documented.

mcp-vstash