creating-letta-code-channels

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a TypeScript utility (scripts/scaffold-user-channel-plugin.ts) designed to be executed via npx tsx. This script automates the creation of directory structures and boilerplate files (JSON and MJS) within the user's home directory under ~/.letta/channels.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an infrastructure for message channel adapters that ingest untrusted data from external sources (e.g., Telegram, Slack) and deliver it to the agent.
  • Ingestion points: Data enters the agent's context through the adapter.onMessage handler, which processes external platform messages as defined in references/user-plugins.md and the scaffolded plugin.mjs.
  • Boundary markers: The skill instructions in SKILL.md and references/first-party-channels.md explicitly advise developers to suppress tool approval prompts on public channels to mitigate the risk of unauthorized command execution via spoofed replies.
  • Capability inventory: Plugins use the MessageChannel tool to enable agent communication. The development environment relies on bun for package management and testing, and npx for scaffolding.
  • Sanitization: The provided plugin skeleton implements a formatText function within its action handler to process outgoing message text, providing a layer of content control.
  • [DYNAMIC_EXECUTION]: The skill facilitates the development of dynamic user plugins that are loaded as external ECMAScript modules (.mjs) at runtime by the platform's channel service.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 06:49 PM