The Agent Skills Directory

[SAFE]: The skill is composed of natural language instructions and examples defining a logical workflow for verifying information. It does not include scripts, binaries, or commands that interact with the host system.
[SAFE]: No obfuscation, data exfiltration, or hardcoded credentials were found. The skill does not attempt to download external packages or execute remote code.
[SAFE]: While the skill is designed to process untrusted input (text to be fact-checked), the workflow's focus on identifying verifiable assertions and categorizing claim types serves as a functional barrier against many forms of indirect prompt injection.

fact-checking