mobile-security-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates user-provided code and application features, creating a surface for indirect prompt injection.
- Ingestion points: User implementation details and audit requests in SKILL.md.
- Boundary markers: The workflow lacks specific delimiters or instructions to ignore embedded commands in analyzed code.
- Capability inventory: No tools, network access, or file-writing capabilities are granted to the skill.
- Sanitization: There is no filtering or sanitization of input data before processing.
Audit Metadata