digital-out-of-home
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for marketing strategy and contains no executable code, network operations, or malicious patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill references external files for context. 1. Ingestion points: .agents/marketing-learnings.md and .agents/marketing-strategy.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no file-write, network, or command-execution tools). 4. Sanitization: Absent. The lack of capabilities to act on external content renders this surface safe.
Audit Metadata