Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent deep-research writing skill, with manageable cautions around broad activation wording and local draft-file creation.
Install this if you want long, sourced research reports. Before using it on sensitive topics, choose a workspace where intermediate draft files are acceptable, confirm filenames or output location, and use a simpler assistant path for quick summaries or ordinary explanations.
The activation criteria are very broad, covering generic requests such as 'detailed report' or 'thorough analysis,' which could cause the skill to trigger in many ordinary interactions. Over-broad triggering increases the chance that a high-autonomy workflow with web access, multilingual searching, and file-writing behaviors is invoked when a simpler or safer response path was intended.
The skill explicitly instructs the agent to create multiple draft files on disk as part of its normal workflow, even though the stated purpose is only to research and produce a report. Unnecessary file creation expands the skill's side effects, can leave sensitive intermediate content behind, and may overwrite or clutter the working environment without clear user consent or operational need.
No suspicious patterns detected.
