mobile-threat-model
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external source code to perform its analysis, which could lead to an indirect prompt injection attack.
- Ingestion points: The skill reads files from the codebase path provided in
$ARGUMENTSor the current working directory using theRead,Glob, andGreptools. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to help it distinguish between its own system instructions and the content of the mobile application files it is analyzing.
- Capability inventory: The agent is granted access to high-privilege tools such as
Bash,Task, andWrite, which could be exploited to perform unauthorized file system operations or command execution if the agent is manipulated by malicious content within the target codebase. - Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content ingested from the external codebase.
Audit Metadata