Collected sources and patterns will appear here. Add from search or the patterns library.
LocalDirectory -> RiskReport
Audit Agent capability definitions and source code for security risks by feeding the directory context to an LLM evaluated against safety taxonomies.
Problem it solves
Traditional static code analysis cannot assess the dynamic semantic risk of Agent tools or autonomous capabilities.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.