The Agent Skills Directory

[SAFE]: The skill provides a set of instructional guidelines for auditing AI agent behavior and verifying evidence. It does not contain any executable scripts, command-line operations, or network requests.
[SAFE]: The instructions emphasize safety by directing the agent to perform only safe, non-destructive verification and to request explicit authorization before modifying state or sending data.
[SAFE]: No patterns associated with prompt injection, data exfiltration, obfuscation, or privilege escalation were detected in the skill's instructions or configuration files.

reality-check