The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions for an LLM to perform logical analysis and classification. It does not include any executable scripts, binary files, or network-enabled commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external artifacts and target claims. While these inputs represent an ingestion point for untrusted data, the skill lacks any capabilities (such as file writes, network requests, or system command execution) that could be leveraged for an attack. No sanitization or boundary markers are explicitly defined, but the lack of active capabilities renders the risk negligible.
[COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or dynamic context injections present in the skill definition.

identify-variables