kmp-state-data
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides best-practice documentation for software architecture. No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were found.
- [NO_CODE]: The skill contains only documentation and guidance files (SKILL.md and Markdown references). It does not include any scripts, binaries, or automated tasks that could execute code.
- [INDIRECT_PROMPT_INJECTION]: While the skill defines patterns for handling external data (network sync, platform interop), it does not provide an active attack surface in its own execution context. It proactively instructs developers to 'Treat cached, migrated, imported, synced, generated, or platform-provided data as untrusted until validated', which acts as a mitigation strategy.
Audit Metadata