The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains detailed instructions and constraints, but no attempts to bypass safety filters or override core agent behavior were found.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill references specific markdown files for style reference but does not attempt to access sensitive system files or exfiltrate data to unauthorized external domains.
[EXTERNAL_DOWNLOADS]: The skill uses a web search tool for fact-checking against authoritative government and banking websites, which is a legitimate and safe use of the tool.
[COMMAND_EXECUTION]: No shell commands or system-level execution patterns were identified.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided notes, it includes a robust fact-checking workflow and a mandatory checklist to ensure content quality and accuracy, mitigating risks of unintended behavior triggered by input.

content-write-article