contagious
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill package is composed entirely of Markdown documentation and reference files. No executable scripts (.py, .js, .sh), binary files, or automated configuration files are included.
- [SAFE]: All external links point to legitimate educational resources or commercial book listings on Amazon. No suspicious or obfuscated URLs were detected during the analysis.
- [SAFE]: The instructions provide guidance for the agent's behavior within the scope of its intended marketing role, without attempting to bypass safety filters or access sensitive system information.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input related to marketing campaigns, creating a theoretical attack surface for indirect prompt injection.
- Ingestion points: User mentions of phrases like "go viral", "word of mouth", or user-supplied design briefs (SKILL.md).
- Boundary markers: Absent; the instructions do not define specific delimiters for user data.
- Capability inventory: The skill enables the agent to generate marketing scores, strategies, and content copy based on provided frameworks.
- Sanitization: Absent; the skill relies on the agent's native capability to handle user input safely.
Audit Metadata