ads-landing
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external landing page URLs, creating a surface for potential indirect prompt injection.
- Ingestion points: External landing page content fetched from user-provided URLs.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts in the analyzed data.
- Capability inventory: Limited to reading project-specific documentation (benchmarks.md, conversion-tracking.md) and generating a report; no code execution or network exfiltration capabilities are present.
- Sanitization: No sanitization or content validation is performed on the analyzed web page content.
Audit Metadata