google-ads-landing
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external landing page URLs provided by the user for auditing purposes. This creates a surface where malicious instructions embedded in the target website's content could influence the agent's behavior.
- Ingestion points: The skill accepts a
<landing page URL>argument as specified inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided in this wrapper file.
- Capability inventory: The skill's stated purpose involves auditing and diagnosing page content, which implies the use of web-reading or browser tools.
- Sanitization: There is no evidence of sanitization or filtering for the content fetched from external URLs within this wrapper.
Audit Metadata