Otc Confirmation

One-Time Confirmation code security mechanism for sensitive agent operations. Generates a cryptographically secure single-use code, delivers it via a private...

Before installing or enabling this skill: 1) Manually inspect the three shell scripts (generate_code.sh, send_otc_email.sh/send_email_smtp.sh, verify_code.sh) to confirm they do not echo the code, do not log secrets, and that credentials are not passed on the command line in a way visible via ps. 2) Run the skill in a non-production sandbox first and test the state-file lifecycle and permission bits (state dir mode 700, state file mode 600). 3) Use a dedicated SMTP account with limited privileges and rotate its password if compromised. 4) If you enable a custom backend script, verify it is trusted and executable only by your user. 5) Be aware the 'agent must not read the state file' is a procedural control — a compromised agent running as the same OS user could read it; consider isolating the guard (different user, container, or stricter sandbox). 6) Note the SKILL.md includes prompt-injection discussion — review the docs and templates so you are comfortable there are no instructions that would weaken your agent's system prompt or security posture. If you want extra assurance, have a security-savvy reviewer audit the scripts for credential handling (curl usage, logging, process args) prior to production use.

Type: OpenClaw Skill Name: otc-confirmation Version: 3.1.0 The 'otc-confirmation' skill bundle is a well-designed security tool providing a human-in-the-loop confirmation mechanism for AI agents. It implements a 'zero-knowledge' architecture where the agent generates and verifies codes via secure local state files (mode 600) without ever seeing the code in its own context or logs. The scripts (generate_code.sh, send_otc_email.sh, verify_code.sh) use cryptographically secure entropy and follow defensive programming practices. Furthermore, the bundle includes an extensive 'Security Architecture Pack' with Python reference implementations for audit logging and permission guarding, specifically designed to protect against prompt injection and unauthorized command execution.