iblai-vibe-agent-disclaimer
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads environment configuration templates and brand assets from the official ibl.ai GitHub repository. These are trusted resources used for project initialization and consistent styling.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the display of agent-provided disclaimer content, which creates a potential surface for indirect injection if the source data is malicious.\n
- Ingestion points: Disclaimer and advisory text is ingested via the
@iblai/iblai-jsSDK components (SKILL.md).\n - Boundary markers: No explicit delimiter or instruction-guarding markers are implemented in the UI examples.\n
- Capability inventory: The skill capabilities include package installation (
pnpm), environment file creation, and automated testing viaplaywright.\n - Sanitization: The skill recommends the use of
react-markdownfor rendering, which provides standard protection for rich text processing.
Audit Metadata