state-of-subscription-apps-2026
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied app performance data (metrics like conversion rates and RPI) to provide benchmarks. This ingestion represents a surface for indirect prompt injection if a user provides malicious instructions disguised as data. Evidence:
- Ingestion points: User-provided metrics and questions described in the 'When someone gives you their own numbers (benchmarking)' section of SKILL.md.
- Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands in user-provided data.
- Capability inventory: The skill is informational and does not contain executable scripts or tools in the provided content.
- Sanitization: No sanitization or validation logic is defined for the external data being processed.
- [SAFE]: The skill references an external URL for the original report. This reference is informational and points to a well-known service provider in the mobile app industry.
- Evidence: Link to RevenueCat's official site: https://www.revenuecat.com/state-of-subscription-apps
Audit Metadata