spoonos-platform-integration
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from multiple external sources and passes it directly to the AI agent. Ingestion points: scripts/telegram_bot.py (Telegram messages), scripts/discord_bot.py (Discord messages and commands), scripts/api_gateway.py (API query field), and SKILL.md (webhook payloads). Boundary markers: The implementation lacks clear delimiters or 'ignore embedded instructions' warnings around external input before processing. Capability inventory: All agents across scripts utilize the core SpoonReactMCP capabilities which are subject to manipulation via the lack of input control. Sanitization: There is no evidence of input validation, escaping, or filtering of the content received from external platforms.
Audit Metadata