skills/iliagerman/agents/buzz/Gen Agent Trust Hub

buzz

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use various CLI tools, including the project-specific buzz CLI, git, docker-compose, and the just build runner to manage project lifecycle and operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies the risk of processing untrusted data from external sources (Nostr relays) and provides explicit instructions to treat such data as non-executable content, mitigating potential injection attacks from channel messages or PR bodies.
  • [SAFE]: All external references and downloads target the official GitHub repository for the Buzz project or well-known services like GitHub Container Registry, which are considered safe sources.
  • [SAFE]: The skill incorporates strong security guidelines, advising the agent to keep private keys (like BUZZ_PRIVATE_KEY) out of logs, code, and commits, and to use environment variables for sensitive configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:18 PM