revenuecat-store-state

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill is designed for legitimate administrative tasks related to RevenueCat and app store management.- [INDIRECT_PROMPT_INJECTION]: The skill manages a potential indirect prompt injection surface by processing external data from store platforms. It includes mandatory safety controls, specifically requiring a user-visible 'before → after' summary and explicit confirmation for all writes to production environments, which effectively mitigates the risk of autonomous obedience to potentially poisoned external metadata.
  • Ingestion points: External product state data is ingested via get-product-store-state (SKILL.md).
  • Boundary markers: The instructions mandate a user-confirmed 'before → after' summary (SKILL.md).
  • Capability inventory: Product state modifications and store submissions via set-product-store-state and submit-products-to-store (SKILL.md).
  • Sanitization: Human-in-the-loop validation via explicit user confirmation before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:42 PM
Security Audit — agent-trust-hub — revenuecat-store-state