marketing-ops
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): No direct prompt injection or behavioral override patterns were detected in the instructions.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from external sources like GitHub releases and marketing platforms, creating an attack surface. ● Ingestion points: GitHub release logs, Google Search Console data, and marketing metrics. ● Boundary markers: None identified in the provided documentation. ● Capability inventory: The skill triggers local script execution (generate.py, cli.py, dashboard.py) and external skill calls (/announce). ● Sanitization: No evidence of input validation or sanitization is provided in the orchestrator file.
- [Dynamic Execution] (LOW): The skill triggers the execution of local Python scripts as part of its core functionality, though no remote code patterns were found.
Audit Metadata