strategy
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is an instructional text prompt designed to guide the agent in generating a marketing strategy. It contains no code, scripts, or commands that would interact with the host system or external networks.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting user-provided data, such as business names and URLs, which creates a theoretical attack surface for indirect prompt injection.
- Ingestion points: Data is collected through user responses to prompts in the 'Gather context' section of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat this data as untrusted.
- Capability inventory: The skill's scope is strictly limited to text generation. It does not utilize any tools for file system modification, network operations, or code execution.
- Sanitization: The instructions do not specify any validation or sanitization for the provided inputs.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes a standard promotional link to the vendor's official website (scalebrick.com). This is a static link provided for user information and does not attempt to exfiltrate session data or credentials.
Audit Metadata