security-app-mobile
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines clear boundaries for sensitive data access by prohibiting the reading of files related to application signing and secrets such as .keystore, .pem, and .mobileprovision files.
- [SAFE]: A strict output contract ensures that sensitive identifiers and user data are redacted before being stored as findings, effectively mitigating the risk of accidental data exposure.
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing untrusted source code projects. 1. Ingestion points: iOS and Android project files and metadata. 2. Boundary markers: The skill includes specific review depths and MASVS control groups to guide the agent's analysis. 3. Capability inventory: Use of file system tools and bash for code search and analysis. 4. Sanitization: Explicit 'redact-first' policy for all findings and forbidden access to cryptographic credentials.
Audit Metadata