authentication-flow-rules
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides industry-standard security guidance for authentication flows, including the mandatory use of PKCE and the removal of the Implicit Flow and Password Credentials flows.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a benign shell command (
cat) to read its internal context file (.claude/context/memory/learnings.md) as part of a 'Memory Protocol'. This is a standard workflow for maintaining state across agent sessions. - [NO_CODE]: The skill package contains no executable scripts or binary files, consisting entirely of markdown instructions and JSON metadata.
Audit Metadata