mobile-app-ui-design
Warn
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill directs the agent to install additional functionality from an external repository (github.com/ceorkm/mobile-app-ui-design) using the
npx skills addcommand. This execution path downloads and runs unverified code from an untrusted third-party source. - [COMMAND_EXECUTION]: The skill uses shell commands during its installation check phase to probe the file system and search for specific patterns using
grep. While these commands are for status detection, they represent the execution of local shell instructions. - [METADATA_POISONING]: The
stub.yamlmetadata includes a 'verified' note with a future date. This is a deceptive claim designed to project a false sense of security and validation that is not backed by the platform's trust system. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to guide mobile UI design based on user input, which creates a surface for indirect prompt injection if malicious instructions are hidden within the design requirements.
- Ingestion points: User-provided mobile UI design requirements (SKILL.md).
- Boundary markers: Absent. The skill does not provide clear delimiters or warnings to ignore instructions embedded in the design data.
- Capability inventory: The skill can execute shell commands and install remote packages (SKILL.md).
- Sanitization: Absent. There is no evidence of input validation or filtering for processed design requirements.
Audit Metadata