kotlin-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates as a senior Kotlin engineer that ingests natural language requests and project context to generate code and architecture (SKILL.md).\n
- Ingestion points: Processes natural language triggers and user-provided technical requirements listed in the core workflow.\n
- Boundary markers: Absent; the instructions do not provide delimiters or "ignore instructions" warnings for external data input.\n
- Capability inventory: Generates complex Kotlin source code, Ktor server configurations, and Gradle build scripts.\n
- Sanitization: Absent; no instructions are provided to sanitize or validate external technical requirements.\n- [SAFE]: No malicious obfuscation, persistence mechanisms, or unauthorized network exfiltration patterns were detected. All external libraries and target frameworks (e.g., Jetpack Compose, Ktor, Kotlinx) are standard, well-known, and trusted within the Kotlin ecosystem. Code examples follow safe practices for credential management by using environment variables or descriptive placeholders.
Audit Metadata