Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward fact-checking helper that uses web research and optional claim extraction to verify and improve factual content.
Install this if you want an agent to fact-check factual drafts using web evidence. Be aware it may trigger on many content-review tasks with factual claims and may suggest rewritten wording; review citations and corrections before applying them to important legal, medical, financial, or public-facing content.
This markdown file says to use the skill "aggressively whenever" the user mentions broad terms like fact-checking, verifying, or validating, and further says to prefer triggering it whenever there is any non-trivial factual content. Those conditions overlap with many ordinary writing and research requests, making the activation scope ambiguous and likely to cause unintended invocation.
The module docstring states that the surrounding skill may 'apply corrections in the user's content,' which is a user-data-affecting action. In this file there is no confirmation flow, warning comment, or user-facing disclosure tied to that behavior, so the code documentation understates a potentially modifying operation.
