landing-page
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses a set of questions to gather information from the user about their product and audience. This user-provided data is then used to generate a landing page outline and copy. While this represents a data ingestion point, the skill possesses no exploitable capabilities such as file system writes, network requests, or shell execution, rendering the risk negligible. 1. Ingestion points: User input gathered through the 'Quick questions' section in SKILL.md. 2. Boundary markers: No specific delimiters or instructions to disregard embedded commands are included. 3. Capability inventory: The skill only generates text output and does not call any tools or scripts. 4. Sanitization: The instructions do not define sanitization or validation for user input.
- [EXTERNAL_DOWNLOADS]: The skill includes external links in REFERENCES.md for further reading. These links point to reputable sources like GitHub and Google's developer documentation and are used for reference only, not for script execution.
Audit Metadata