landing-copy
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from user-provided URLs. Ingestion points: Phase 1 instructs the agent to fetch and read copy from a URL. Boundary markers: There are no instructions to the agent to treat this fetched content as data rather than instructions. Capability inventory: The skill does not possess high-risk capabilities such as file modification or subprocess execution. Sanitization: No sanitization or filtering logic is present for external content.
Audit Metadata