kotlin-multiplatform
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): No malicious patterns or security vulnerabilities detected. The skill consists of standard documentation and code examples for KMP development.- PROMPT_INJECTION (SAFE): No evidence of instructions attempting to bypass safety filters or override agent constraints.- DATA_EXFILTRATION (SAFE): Network patterns identified (Ktor HTTP client) use placeholder domains (api.example.com) and represent standard application code templates rather than exfiltration attempts.- EXTERNAL_DOWNLOADS (SAFE): The skill defines project dependencies in Gradle configuration but does not attempt to download or execute remote scripts during its own execution.- INDIRECT_PROMPT_INJECTION (SAFE): While the skill provides templates for apps that handle external data, the skill itself does not ingest or process untrusted external content in a way that poses a risk to the agent.
Audit Metadata