mmp-setup
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown, providing checklists and advice for app marketing attribution. It does not contain any executable scripts, shell commands, or automated tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface as it instructs the agent to read external context files (
app-ads-context.mdandapp-marketing-context.md). - Ingestion points: Initial Assessment section (Step 1).
- Boundary markers: None explicitly defined for file reading.
- Capability inventory: None. The skill lacks subprocess calls, network operations, or file-writing capabilities.
- Sanitization: Not applicable as the skill only provides text-based guidance to the user.
- [SAFE]: No hardcoded credentials, obfuscation, or persistence mechanisms were detected. The skill references well-known industry services (AppsFlyer, Adjust, TikTok, Meta) in a standard marketing context.
Audit Metadata