mobile-ui-development-rule
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is configured to ingest and process external code files matching the glob
**/mobile/**/*.*usingRead,Write, andEdittools. This creates an indirect prompt injection surface where malicious instructions embedded in the mobile source code could attempt to influence the agent's behavior. - Ingestion points: Source files matching
**/mobile/**/*.*referenced inSKILL.md. - Boundary markers: None identified in the provided instructions.
- Capability inventory: Access to
Read,Write, andEdittools as defined inSKILL.md. - Sanitization: No explicit sanitization, escaping, or validation of the processed file content is documented.
- [COMMAND_EXECUTION]: The
SKILL.mdfile contains a 'Memory Protocol' section that instructs the agent to execute a shell command (cat .claude/context/memory/learnings.md) to retrieve state information. While the command targets internal context files and is intended for state management, it represents a direct command execution instruction.
Audit Metadata