The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package from the official NPM registry, which is the legitimate command-line interface provided by the vendor for platform interaction.
[COMMAND_EXECUTION]: Employs the Membrane CLI to perform Asana operations such as listing tasks, creating projects, and running actions.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from Asana tasks and projects.
Ingestion points: External data enters the context through actions like list-tasks, get-task, and list-project-tasks as documented in SKILL.md.
Boundary markers: None identified; external content is processed without specific delimiters or instructions to ignore embedded commands.
Capability inventory: The skill can execute state-changing actions via membrane action run, including task and project creation, updates, and deletion.
Sanitization: No explicit sanitization or validation of external content is present in the skill instructions.
[SAFE]: The skill promotes secure practices by utilizing Membrane's managed connection system for authentication, ensuring that no API keys or tokens are handled or requested locally.

asana