marketing
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Remote Code Execution] (SAFE): No executable scripts, binaries, or package manager files (requirements.txt, package.json) are included in the skill.
- [Data Exfiltration] (SAFE): No network operations (curl, wget, fetch) or credential-accessing patterns were detected.
- [Prompt Injection] (SAFE): The 'Non-Negotiable' tone instructions are stylistic constraints and do not attempt to override the agent's safety protocols or core system instructions.
- [Indirect Prompt Injection] (LOW):
- Ingestion points: The skill ingests untrusted product descriptions, theme details, and plugin information from users to generate content.
- Boundary markers: None. There are no instructions to use delimiters or ignore instructions within the source material.
- Capability inventory: File-write operations (creating markdown files in the 'marketing/' folder structure).
- Sanitization: None. The skill does not specify validation or sanitization of the input product data.
Audit Metadata