The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the user to install the @membranehq/cli package globally via the npm registry. This is the official command-line interface for the Membrane platform, which the skill uses to manage authentication and API interactions.
[COMMAND_EXECUTION]: The skill instructions involve executing various shell commands through the membrane CLI to authenticate users, establish connections to AssemblyAI, and run transcription actions.
[INDIRECT_PROMPT_INJECTION]: The skill processes transcription data (sentences, paragraphs, and summaries) retrieved from external audio/video files via AssemblyAI. This content enters the agent's context as untrusted data.
Ingestion points: Transcript data retrieved from AssemblyAI API endpoints in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the transcript text.
Capability inventory: The skill allows for network operations and CLI-based command execution via the Membrane toolset.
Sanitization: There is no evidence of sanitization or filtering of the processed transcript content before it is displayed or used by the agent.

assemblyai