appmigrationkit
Warn
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: MEDIUMMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill documentation refers to fictitious software versions (iOS 26.0+) and utilizes an unofficial domain (sosumi.ai) for all technical documentation links instead of official developer resources. This misleading information could cause developers or agents to rely on non-existent APIs or untrusted documentation sources.
- [INDIRECT_PROMPT_INJECTION]: The skill provides implementation patterns for importing external data from untrusted sources into the application's secure container and shared app groups. This functionality lacks robust content validation, creating a potential vector for malicious data to influence the system.
- Ingestion points: The
importResourcesmethod inreferences/appmigrationkit-patterns.mdandreferences/core-implementation.mdaccepts an externalURLto imported resources. - Boundary markers: No delimiters or isolation techniques are recommended for the ingested data to prevent it from being interpreted as instructions.
- Capability inventory: The skill utilizes
FileManagerto perform write operations within the app container and security application groups. - Sanitization: The provided code snippets perform direct file copying operations without verifying the integrity or safety of the ingested content.
Audit Metadata