spectacles-connected-lenses

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides technical documentation and code samples for official Snapchat developer tools including ConnectedLensesModule, LensCloud, and SpectaclesSyncKit. No malicious patterns, obfuscation, or unauthorized data access techniques were identified.
  • [PROMPT_INJECTION]: The skill describes networking APIs that ingest data from other users, which technically presents a surface for indirect prompt injection. However, the documentation proactively addresses this by teaching developers how to implement robust validation logic.
  • Ingestion points: Data is ingested via RealtimeStore.onValueChanged (SKILL.md) and NetworkEventSystem.on (references/sync-kit-components.md).
  • Boundary markers: Not applicable to this type of API reference.
  • Capability inventory: Capability is limited to updating local game states, UI elements, and physics object transforms within the AR environment.
  • Sanitization: The skill provides explicit examples of input validation, checking data types with typeof and ensuring numeric values are within safe ranges using isFinite and bounds checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 04:22 PM