The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the official @membranehq/cli from the NPM registry to enable platform integration.
[COMMAND_EXECUTION]: Executes shell commands via the membrane CLI to manage authentication, connection states, and security workflows.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external action outputs and user-supplied intents.
Ingestion points: Untrusted data from external security scans enters the context via membrane action run outputs in SKILL.md.
Boundary markers: No delimiters or instructions to ignore embedded directives are used in the provided templates.
Capability inventory: The agent can invoke various security operations and manage system connections via the membrane CLI in SKILL.md.
Sanitization: No sanitization of output from the security platform is performed before processing.

whitehat-security