Lel Mail

This skill largely does what it says (send/read emails), but there are several things to check before installing or enabling it: - Missing declared dependency: the scripts call 'openclaw agent' but the skill only declares python3. Ensure the 'openclaw' CLI is present and you understand what it can do — the skill relies on it to invoke LLM-driven actions and to write to agent memory. - Sensitive credentials: the skill requires a plaintext ~/.config/lel-mail/config.json with account passwords/app-specific passwords. Store that file with strict permissions and consider using app-specific passwords or a dedicated throwaway account. Audit the config storage and rotate credentials if needed. - Broad agent actions: the skill instructs the agent to scan memory banks, write to MEMORY.md, locate user sessions, and proactively contact users. If you don't want the agent to modify its memory or contact users automatically, do not enable autonomous invocation or avoid installing the cron job. - Cron persistence: the SKILL.md asks you to add a cron entry for periodic sending. If you install that, the skill can send queued emails automatically. Only add the cron job if you trust the configuration and have reviewed the scripts. - Recommended mitigations: run in an isolated environment (container or dedicated account), inspect/modify scripts to require explicit confirmation before sending, restrict file permissions on ~/.config/lel-mail, and ensure the 'openclaw' CLI has expected behavior and access controls. If you need clarification from the author (unknown source), ask why 'openclaw' isn't declared and whether the LLM-driven write-to-memory behavior can be limited.