iii-reactive-backend

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for using the iii engine's built-in functions. The author (iii-hq) utilizes its own platform modules (state, stream, http) which is consistent with the stated purpose. No suspicious behaviors such as credential theft or unauthorized network communication were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes an architecture that processes external data via HTTP and state-based triggers, creating a potential surface for indirect prompt injection. 1. Ingestion points: External data enters via 'registerTrigger' for 'http' and 'state' events as seen in SKILL.md. 2. Boundary markers: No specific delimiters or safety warnings for embedded instructions are present in the documentation. 3. Capability inventory: The skill utilizes capabilities for state modification (state::set) and network broadcasting (stream::send) in SKILL.md. 4. Sanitization: The provided patterns do not explicitly mention sanitization or validation of input data. Implementation of this pattern should include strict data validation to mitigate injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:34 PM