ads-landing

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external landing pages, which constitutes an ingestion point for untrusted third-party data.
  • Ingestion points: External landing pages, redirects, frames, and scripts fetched during the audit process (SKILL.md).
  • Boundary markers: The instructions explicitly state to treat all fetched content as untrusted and forbid the execution of instructions found within the audited pages.
  • Capability inventory: Uses a guarded HTTP fetcher and potentially a sandboxed browser to retrieve external content.
  • Sanitization: Includes specific protocols for DNS pinning, egress sandboxing, and strict blocking of private, loopback, link-local, and cloud-metadata IP destinations to mitigate Server-Side Request Forgery (SSRF) and data exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:07 PM
Security Audit — agent-trust-hub — ads-landing