landing-page-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites, which could contain malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: Uses WebFetch to load content from user-provided URLs and WebSearch to retrieve data from competitor websites.
- Boundary markers: The instructions do not specify any delimiters (like XML tags or triple quotes) or 'ignore embedded instructions' directives to isolate external content from the agent's operational logic.
- Capability inventory: The skill is configured with access to high-capability tools including Bash, Write, Read, WebFetch, and WebSearch in its allowed-tools configuration.
- Sanitization: There is no mention of sanitizing, filtering, or validating the external content before it is processed by the agent.
Audit Metadata