The Agent Skills Directory

[Prompt Injection] (SAFE): The instructions are purely navigational and do not contain any patterns attempting to override agent behavior or bypass safety constraints.
[Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network transmission logic were detected.
[Remote Code Execution] (SAFE): There are no patterns involving the download or execution of remote scripts (e.g., curl | bash).
[Command Execution] (SAFE): The skill does not invoke any system-level commands, shell scripts, or binary executions.
[Obfuscation] (SAFE): No Base64 encoding, zero-width characters, or homoglyphs were found.
[Indirect Prompt Injection] (LOW): As a router, this skill processes user input to select a downstream tool. While it lacks explicit sanitization markers, its primary capability is redirection to other skills, which constitutes a standard operational surface with no elevated risk.

axiom-shipping