iblai-agent-history
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches images, brand guidelines, and environment templates from the vendor's official GitHub repository (iblai/vibe).
- [COMMAND_EXECUTION]: Instructs the user to run standard package management commands (pip, npm, pnpm) to install official vendor CLI tools and libraries.
- [PROMPT_INJECTION]: The skill implements a UI for rendering conversation history, which is an indirect prompt injection surface.
- Ingestion points: The renderMessageContent prop in AgentHistoryTab processes conversation content strings.
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are provided in the snippet.
- Capability inventory: The component renders messages to the browser using ReactMarkdown.
- Sanitization: Content is rendered via ReactMarkdown, which offers basic XSS protection but does not prevent the agent from acting on instructions contained within the history data.
Audit Metadata