The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry. This package is the primary tool for managing integrations provided by the vendor.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform authentication, query available actions, and execute data workflows.
[PROMPT_INJECTION]: The skill processes data returned from external actions, which represents a surface for indirect prompt injection.
Ingestion points: Results from membrane action list and membrane action run commands in SKILL.md.
Boundary markers: Absent; the agent is not instructed to use specific delimiters or ignore embedded instructions within action outputs.
Capability inventory: Shell command execution via the membrane CLI in SKILL.md.
Sanitization: Absent; the skill instructions do not include steps to validate or sanitize external output before processing.

vectorizedio