skills/letta-ai/lettabot/bluesky/Gen Agent Trust Hub

bluesky

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The lettabot-bluesky script functions as a shim to execute the Bluesky CLI tool. It prioritizes project-local entry points before falling back to the lettabot binary found on the system path.
  • [SAFE]: Indirect Prompt Injection Risk: The skill consumes data from external Bluesky sources. Ingestion points: timeline, notifications, search, thread, and author-feed commands in SKILL.md. Boundary markers: None identified. Capability inventory: post, reply, like, repost, mute, and block commands. Sanitization: No explicit content filtering or sanitization of external data is defined in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:50 PM