The Agent Skills Directory

[PROMPT_INJECTION]: The CLI enables the ingestion of external data from URLs, files, and third-party connectors (via supermemory add and supermemory connectors), which is then indexed for semantic search and profiling. This architecture presents a surface for indirect prompt injection if malicious instructions are embedded in the ingested sources. * Ingestion points: supermemory add (accepting text, files, and URLs) and supermemory connectors (syncing from Google Drive, Notion, etc.) as seen in SKILL.md. * Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for ingested content. * Capability inventory: The CLI tool possesses capabilities for reading local files, making network requests to external URLs, and managing administrative resources like API keys and team roles. * Sanitization: No sanitization or validation routines for external content are mentioned in the documentation.
[COMMAND_EXECUTION]: The documentation includes commands for sensitive administrative tasks, such as creating and revoking API keys (supermemory keys), managing team members and roles (supermemory team), and setting configuration values (supermemory config).
[EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the official CLI tool from the @supermemory/cli NPM package, which is a standard procedure from the tool's vendor.

supermemory-cli